Merge branch 'main' into prune-samplers-test

[Bug] Fix R1 Accuracy 0 Bug (#23294 )
Signed-off-by: yewentao256 <zhyanwentao@126.com> Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com> Co-authored-by: Michael Goin <mgoin64@gmail.com>
2025-10-20 23:03:52 +08:00 · 2025-08-21 10:15:16 -07:00 · 2025-08-21 13:11:28 -04:00 · 2025-08-21 17:05:47 +00:00 · 2025-08-21 16:54:50 +00:00 · 2025-08-21 16:54:08 +00:00
1267 changed files with 83046 additions and 43108 deletions
--- a/.buildkite/generate_index.py
+++ b/.buildkite/generate_index.py
@ -8,7 +8,8 @@ template = """<!DOCTYPE html>
 <html>
    <body>
    <h1>Links for vLLM</h1/>
-        <a href="../{wheel_html_escaped}">{wheel}</a><br/>
+        <a href="../{x86_wheel_html_escaped}">{x86_wheel}</a><br/>
+        <a href="../{arm_wheel_html_escaped}">{arm_wheel}</a><br/>
    </body>
 </html>
 """
@ -21,7 +22,25 @@ filename = os.path.basename(args.wheel)

 with open("index.html", "w") as f:
    print(f"Generated index.html for {args.wheel}")
+    # sync the abi tag with .buildkite/scripts/upload-wheels.sh
+    if "x86_64" in filename:
+        x86_wheel = filename
+        arm_wheel = filename.replace("x86_64", "aarch64").replace(
+            "manylinux1", "manylinux2014"
+        )
+    elif "aarch64" in filename:
+        x86_wheel = filename.replace("aarch64", "x86_64").replace(
+            "manylinux2014", "manylinux1"
+        )
+        arm_wheel = filename
+    else:
+        raise ValueError(f"Unsupported wheel: {filename}")
    # cloudfront requires escaping the '+' character
    f.write(
-        template.format(wheel=filename, wheel_html_escaped=filename.replace("+", "%2B"))
+        template.format(
+            x86_wheel=x86_wheel,
+            x86_wheel_html_escaped=x86_wheel.replace("+", "%2B"),
+            arm_wheel=arm_wheel,
+            arm_wheel_html_escaped=arm_wheel.replace("+", "%2B"),
+        )
    )
--- a/.buildkite/lm-eval-harness/configs/Meta-Llama-3-8B-QQQ.yaml
+++ b/.buildkite/lm-eval-harness/configs/Meta-Llama-3-8B-QQQ.yaml
@ -1,12 +0,0 @@
-# For vllm script, with -t option (tensor parallel size).
-# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m HandH1998/QQQ-Llama-3-8b-g128 -b 32 -l 1000 -f 5 -t 1
-model_name: "HandH1998/QQQ-Llama-3-8b-g128"
-tasks:
- name: "gsm8k"
-  metrics:
-  - name: "exact_match,strict-match"
-    value: 0.419
-  - name: "exact_match,flexible-extract"
-    value: 0.416
-limit: 1000
-num_fewshot: 5
--- a/.buildkite/lm-eval-harness/configs/models-large.txt
+++ b/.buildkite/lm-eval-harness/configs/models-large.txt
@ -3,4 +3,3 @@ Meta-Llama-3-70B-Instruct.yaml
 Mixtral-8x7B-Instruct-v0.1.yaml
 Qwen2-57B-A14-Instruct.yaml
 DeepSeek-V2-Lite-Chat.yaml
-Meta-Llama-3-8B-QQQ.yaml
--- a/.buildkite/nightly-benchmarks/README.md
+++ b/.buildkite/nightly-benchmarks/README.md
@ -7,7 +7,7 @@ This directory contains two sets of benchmark for vllm.
 - Performance benchmark: benchmark vllm's performance under various workload, for **developers** to gain clarity on whether their PR improves/degrades vllm's performance
 - Nightly benchmark: compare vllm's performance against alternatives (tgi, trt-llm and lmdeploy), for **the public** to know when to choose vllm.

-See [vLLM performance dashboard](https://perf.vllm.ai) for the latest performance benchmark results and [vLLM GitHub README](https://github.com/vllm-project/vllm/blob/main/README.md) for latest nightly benchmark results.
+See [vLLM performance dashboard](https://hud.pytorch.org/benchmark/llms?repoName=vllm-project%2Fvllm) for the latest performance benchmark results and [vLLM GitHub README](https://github.com/vllm-project/vllm/blob/main/README.md) for latest nightly benchmark results.

 ## Performance benchmark quick overview

@ -28,6 +28,7 @@ See [vLLM performance dashboard](https://perf.vllm.ai) for the latest performanc
 ## Trigger the benchmark

 Performance benchmark will be triggered when:
+
 - A PR being merged into vllm.
 - Every commit for those PRs with `perf-benchmarks` label AND `ready` label.

@ -38,6 +39,7 @@ bash .buildkite/nightly-benchmarks/scripts/run-performance-benchmarks.sh
 ```

 Runtime environment variables:
+
 - `ON_CPU`: set the value to '1' on Intel® Xeon® Processors. Default value is 0.
 - `SERVING_JSON`: JSON file to use for the serving tests. Default value is empty string (use default file).
 - `LATENCY_JSON`: JSON file to use for the latency tests. Default value is empty string (use default file).
@ -46,12 +48,14 @@ Runtime environment variables:
 - `REMOTE_PORT`: Port for the remote vLLM service to benchmark. Default value is empty string.

 Nightly benchmark will be triggered when:
+
 - Every commit for those PRs with `perf-benchmarks` label and `nightly-benchmarks` label.

 ## Performance benchmark details

 See [performance-benchmarks-descriptions.md](performance-benchmarks-descriptions.md) for detailed descriptions, and use `tests/latency-tests.json`, `tests/throughput-tests.json`, `tests/serving-tests.json` to configure the test cases.
 > NOTE: For Intel® Xeon® Processors, use `tests/latency-tests-cpu.json`, `tests/throughput-tests-cpu.json`, `tests/serving-tests-cpu.json` instead.
+>
 ### Latency test

 Here is an example of one test inside `latency-tests.json`:
@ -74,7 +78,7 @@ Here is an example of one test inside `latency-tests.json`:
 In this example:

 - The `test_name` attributes is a unique identifier for the test. In `latency-tests.json`, it must start with `latency_`.
- The `parameters` attribute control the command line arguments to be used for `benchmark_latency.py`. Note that please use underline `_` instead of the dash `-` when specifying the command line arguments, and `run-performance-benchmarks.sh` will convert the underline to dash when feeding the arguments to `benchmark_latency.py`. For example, the corresponding command line arguments for `benchmark_latency.py` will be `--model meta-llama/Meta-Llama-3-8B --tensor-parallel-size 1 --load-format dummy --num-iters-warmup 5 --num-iters 15`
+- The `parameters` attribute control the command line arguments to be used for `vllm bench latency`. Note that please use underline `_` instead of the dash `-` when specifying the command line arguments, and `run-performance-benchmarks.sh` will convert the underline to dash when feeding the arguments to `vllm bench latency`. For example, the corresponding command line arguments for `vllm bench latency` will be `--model meta-llama/Meta-Llama-3-8B --tensor-parallel-size 1 --load-format dummy --num-iters-warmup 5 --num-iters 15`

 Note that the performance numbers are highly sensitive to the value of the parameters. Please make sure the parameters are set correctly.

@ -82,13 +86,13 @@ WARNING: The benchmarking script will save json results by itself, so please do

 ### Throughput test

-The tests are specified in `throughput-tests.json`. The syntax is similar to `latency-tests.json`, except for that the parameters will be fed forward to `benchmark_throughput.py`.
+The tests are specified in `throughput-tests.json`. The syntax is similar to `latency-tests.json`, except for that the parameters will be fed forward to `vllm bench throughput`.

 The number of this test is also stable -- a slight change on the value of this number might vary the performance numbers by a lot.

 ### Serving test

-We test the throughput by using `benchmark_serving.py` with request rate = inf to cover the online serving overhead. The corresponding parameters are in `serving-tests.json`, and here is an example:
+We test the throughput by using `vllm bench serve` with request rate = inf to cover the online serving overhead. The corresponding parameters are in `serving-tests.json`, and here is an example:

 ```json
 [
@ -100,7 +104,6 @@ We test the throughput by using `benchmark_serving.py` with request rate = inf t
            "tensor_parallel_size": 1,
            "swap_space": 16,
            "disable_log_stats": "",
-            "disable_log_requests": "",
            "load_format": "dummy"
        },
        "client_parameters": {
@ -118,8 +121,8 @@ Inside this example:

 - The `test_name` attribute is also a unique identifier for the test. It must start with `serving_`.
 - The `server-parameters` includes the command line arguments for vLLM server.
- The `client-parameters` includes the command line arguments for `benchmark_serving.py`.
- The `qps_list` controls the list of qps for test. It will be used to configure the `--request-rate` parameter in `benchmark_serving.py`
+- The `client-parameters` includes the command line arguments for `vllm bench serve`.
+- The `qps_list` controls the list of qps for test. It will be used to configure the `--request-rate` parameter in `vllm bench serve`

 The number of this test is less stable compared to the delay and latency benchmarks (due to randomized sharegpt dataset sampling inside `benchmark_serving.py`), but a large change on this number (e.g. 5% change) still vary the output greatly.

@ -135,27 +138,20 @@ The raw benchmarking results (in the format of json files) are in the `Artifacts

 The `compare-json-results.py` helps to compare benchmark results JSON files converted using `convert-results-json-to-markdown.py`.
 When run, benchmark script generates results under `benchmark/results` folder, along with the `benchmark_results.md` and `benchmark_results.json`.
-`compare-json-results.py` compares two `benchmark_results.json` files and provides performance ratio e.g. for Output Tput, Median TTFT and Median TPOT.
+`compare-json-results.py` compares two `benchmark_results.json` files and provides performance ratio e.g. for Output Tput, Median TTFT and Median TPOT.  
+If only one benchmark_results.json is passed, `compare-json-results.py` compares different TP and PP configurations in the benchmark_results.json instead.

-Here is an example using the script to compare result_a and result_b without detail test name.
-`python3 compare-json-results.py -f results_a/benchmark_results.json -f results_b/benchmark_results.json --ignore_test_name`
-
-|    | results_a/benchmark_results.json | results_b/benchmark_results.json | perf_ratio        |
-|----|----------------------------------------|----------------------------------------|----------|
-| 0  | 142.633982                             | 156.526018                             | 1.097396 |
-| 1  | 241.620334                             | 294.018783                             | 1.216863 |
-| 2  | 218.298905                             | 262.664916                             | 1.203235 |
-| 3  | 242.743860                             | 299.816190                             | 1.235113 |
-
-Here is an example using the script to compare result_a and result_b with detail test name.
+Here is an example using the script to compare result_a and result_b with Model, Dataset name, input/output lenght, max concurrency and qps.
 `python3 compare-json-results.py -f results_a/benchmark_results.json -f results_b/benchmark_results.json`
-|   | results_a/benchmark_results.json_name | results_a/benchmark_results.json | results_b/benchmark_results.json_name | results_b/benchmark_results.json | perf_ratio        |
-|---|---------------------------------------------|----------------------------------------|---------------------------------------------|----------------------------------------|----------|
-| 0 | serving_llama8B_tp1_sharegpt_qps_1          | 142.633982                             | serving_llama8B_tp1_sharegpt_qps_1          | 156.526018                             | 1.097396 |
-| 1 | serving_llama8B_tp1_sharegpt_qps_16         | 241.620334                             | serving_llama8B_tp1_sharegpt_qps_16         | 294.018783                             | 1.216863 |
-| 2 | serving_llama8B_tp1_sharegpt_qps_4          | 218.298905                             | serving_llama8B_tp1_sharegpt_qps_4          | 262.664916                             | 1.203235 |
-| 3 | serving_llama8B_tp1_sharegpt_qps_inf        | 242.743860                             | serving_llama8B_tp1_sharegpt_qps_inf        | 299.816190                             | 1.235113 |
-| 4 | serving_llama8B_tp2_random_1024_128_qps_1   | 96.613390                              | serving_llama8B_tp4_random_1024_128_qps_1   | 108.404853                             | 1.122048 |
+
+|   | Model | Dataset Name | Input Len | Output Len | # of max concurrency | qps  | results_a/benchmark_results.json | results_b/benchmark_results.json | perf_ratio        |
+|----|---------------------------------------|--------|-----|-----|------|-----|-----------|----------|----------|
+| 0  | meta-llama/Meta-Llama-3.1-8B-Instruct | random | 128 | 128 | 1000 | 1 | 142.633982                             | 156.526018                             | 1.097396 |
+| 1  | meta-llama/Meta-Llama-3.1-8B-Instruct | random | 128 | 128 | 1000 | inf| 241.620334                             | 294.018783                             | 1.216863 |
+
+A comparison diagram will be generated below the table.
+Here is an example to compare between 96c/results_gnr_96c_091_tp2pp3 and 128c/results_gnr_128c_091_tp2pp3
+<img width="1886" height="828" alt="image" src="https://github.com/user-attachments/assets/c02a43ef-25d0-4fd6-90e5-2169a28682dd" />

 ## Nightly test details

@ -164,9 +160,9 @@ See [nightly-descriptions.md](nightly-descriptions.md) for the detailed descript
 ### Workflow

 - The [nightly-pipeline.yaml](nightly-pipeline.yaml) specifies the docker containers for different LLM serving engines.
- Inside each container, we run [run-nightly-suite.sh](run-nightly-suite.sh), which will probe the serving engine of the current container.
- The `run-nightly-suite.sh` will redirect the request to `tests/run-[llm serving engine name]-nightly.sh`, which parses the workload described in [nightly-tests.json](tests/nightly-tests.json) and performs the benchmark.
- At last, we run [scripts/plot-nightly-results.py](scripts/plot-nightly-results.py) to collect and plot the final benchmarking results, and update the results to buildkite.
+- Inside each container, we run [scripts/run-nightly-benchmarks.sh](scripts/run-nightly-benchmarks.sh), which will probe the serving engine of the current container.
+- The `scripts/run-nightly-benchmarks.sh` will parse the workload described in [nightly-tests.json](tests/nightly-tests.json) and launch the right benchmark for the specified serving engine via `scripts/launch-server.sh`.
+- At last, we run [scripts/summary-nightly-results.py](scripts/summary-nightly-results.py) to collect and plot the final benchmarking results, and update the results to buildkite.

 ### Nightly tests

@ -176,6 +172,6 @@ In [nightly-tests.json](tests/nightly-tests.json), we include the command line a

 The docker containers for benchmarking are specified in `nightly-pipeline.yaml`.

-WARNING: the docker versions are HARD-CODED and SHOULD BE ALIGNED WITH `nightly-descriptions.md`. The docker versions need to be hard-coded as there are several version-specific bug fixes inside `tests/run-[llm serving engine name]-nightly.sh`.
+WARNING: the docker versions are HARD-CODED and SHOULD BE ALIGNED WITH `nightly-descriptions.md`. The docker versions need to be hard-coded as there are several version-specific bug fixes inside `scripts/run-nightly-benchmarks.sh` and `scripts/launch-server.sh`.

 WARNING: populating `trt-llm` to latest version is not easy, as it requires updating several protobuf files in [tensorrt-demo](https://github.com/neuralmagic/tensorrt-demo.git).
--- a/.buildkite/nightly-benchmarks/nightly-annotation.md
+++ b/.buildkite/nightly-benchmarks/nightly-annotation.md
@ -1,3 +1,4 @@
+# Nightly benchmark annotation

 ## Description

@ -13,15 +14,15 @@ Please download the visualization scripts in the post

 - Find the docker we use in `benchmarking pipeline`
 - Deploy the docker, and inside the docker:
-  - Download `nightly-benchmarks.zip`.
-  - In the same folder, run the following code:
+    - Download `nightly-benchmarks.zip`.
+    - In the same folder, run the following code:

-  ```bash
-  export HF_TOKEN=<your HF token>
-  apt update
-  apt install -y git
-  unzip nightly-benchmarks.zip
-  VLLM_SOURCE_CODE_LOC=./ bash .buildkite/nightly-benchmarks/scripts/run-nightly-benchmarks.sh
-  ```
+    ```bash
+    export HF_TOKEN=<your HF token>
+    apt update
+    apt install -y git
+    unzip nightly-benchmarks.zip
+    VLLM_SOURCE_CODE_LOC=./ bash .buildkite/nightly-benchmarks/scripts/run-nightly-benchmarks.sh
+    ```

 And the results will be inside `./benchmarks/results`.
--- a/.buildkite/nightly-benchmarks/nightly-descriptions.md
+++ b/.buildkite/nightly-benchmarks/nightly-descriptions.md
@ -13,25 +13,25 @@ Latest reproduction guilde: [github issue link](https://github.com/vllm-project/
 ## Setup

 - Docker images:
-  - vLLM: `vllm/vllm-openai:v0.6.2`
-  - SGLang: `lmsysorg/sglang:v0.3.2-cu121`
-  - LMDeploy: `openmmlab/lmdeploy:v0.6.1-cu12`
-  - TensorRT-LLM: `nvcr.io/nvidia/tritonserver:24.07-trtllm-python-py3`
-    - *NOTE: we uses r24.07 as the current implementation only works for this version. We are going to bump this up.*
-  - Check [nightly-pipeline.yaml](nightly-pipeline.yaml) for the concrete docker images, specs and commands we use for the benchmark.
+    - vLLM: `vllm/vllm-openai:v0.6.2`
+    - SGLang: `lmsysorg/sglang:v0.3.2-cu121`
+    - LMDeploy: `openmmlab/lmdeploy:v0.6.1-cu12`
+    - TensorRT-LLM: `nvcr.io/nvidia/tritonserver:24.07-trtllm-python-py3`
+        - *NOTE: we uses r24.07 as the current implementation only works for this version. We are going to bump this up.*
+    - Check [nightly-pipeline.yaml](nightly-pipeline.yaml) for the concrete docker images, specs and commands we use for the benchmark.
 - Hardware
-  - 8x Nvidia A100 GPUs
+    - 8x Nvidia A100 GPUs
 - Workload:
-  - Dataset
-    - ShareGPT dataset
-    - Prefill-heavy dataset (in average 462 input tokens, 16 tokens as output)
-    - Decode-heavy dataset (in average 462 input tokens, 256 output tokens)
-    - Check [nightly-tests.json](tests/nightly-tests.json) for the concrete configuration of datasets we use.
-  - Models: llama-3 8B, llama-3 70B.
-    - We do not use llama 3.1 as it is incompatible with trt-llm r24.07. ([issue](https://github.com/NVIDIA/TensorRT-LLM/issues/2105)).
-  - Average QPS (query per second): 2, 4, 8, 16, 32 and inf.
-    - Queries are randomly sampled, and arrival patterns are determined via Poisson process, but all with fixed random seed.
-  - Evaluation metrics: Throughput (higher the better), TTFT (time to the first token, lower the better), ITL (inter-token latency, lower the better).
+    - Dataset
+        - ShareGPT dataset
+        - Prefill-heavy dataset (in average 462 input tokens, 16 tokens as output)
+        - Decode-heavy dataset (in average 462 input tokens, 256 output tokens)
+        - Check [nightly-tests.json](tests/nightly-tests.json) for the concrete configuration of datasets we use.
+    - Models: llama-3 8B, llama-3 70B.
+        - We do not use llama 3.1 as it is incompatible with trt-llm r24.07. ([issue](https://github.com/NVIDIA/TensorRT-LLM/issues/2105)).
+    - Average QPS (query per second): 2, 4, 8, 16, 32 and inf.
+        - Queries are randomly sampled, and arrival patterns are determined via Poisson process, but all with fixed random seed.
+    - Evaluation metrics: Throughput (higher the better), TTFT (time to the first token, lower the better), ITL (inter-token latency, lower the better).

 ## Known issues

--- a/.buildkite/nightly-benchmarks/performance-benchmarks-descriptions.md
+++ b/.buildkite/nightly-benchmarks/performance-benchmarks-descriptions.md
@ -1,3 +1,4 @@
+# Performance benchmarks descriptions

 ## Latency tests

--- a/.buildkite/nightly-benchmarks/scripts/compare-json-results.py
+++ b/.buildkite/nightly-benchmarks/scripts/compare-json-results.py
@ -1,33 +1,202 @@
 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 import argparse
+import json
+import os
+from importlib import util

 import pandas as pd

+plotly_found = util.find_spec("plotly.express") is not None
+

 def compare_data_columns(
-    files, name_column, data_column, drop_column, ignore_test_name=False
+    files, name_column, data_column, info_cols, drop_column, debug=False
 ):
-    print("\ncompare_data_column: " + data_column)
-    frames = []
-    compare_frames = []
-    for file in files:
-        data_df = pd.read_json(file)
-        serving_df = data_df.dropna(subset=[drop_column], ignore_index=True)
-        if ignore_test_name is False:
-            serving_df = serving_df.rename(columns={name_column: file + "_name"})
-            frames.append(serving_df[file + "_name"])
-        serving_df = serving_df.rename(columns={data_column: file})
-        frames.append(serving_df[file])
-        compare_frames.append(serving_df[file])
-        if len(compare_frames) >= 2:
-            # Compare numbers among two files
-            ratio_df = compare_frames[1] / compare_frames[0]
-            frames.append(ratio_df)
-            compare_frames.pop(1)
+    """
+    Align concatenation by keys derived from info_cols instead of row order.
+    - Pick one canonical key list: subset of info_cols present in ALL files.
+    - For each file: set index to those keys, aggregate duplicates
+    - (mean for metric, first for names).
+    - Concat along axis=1 (indexes align), then reset_index so callers can
+    - group by columns.
+    - If --debug, add a <file_label>_name column per file.
+    """
+    print("\ncompare_data_column:", data_column)

+    frames = []
+    raw_data_cols = []
+    compare_frames = []
+
+    # 1) choose a canonical key list from info_cols that exists in ALL files
+    cols_per_file = []
+    for f in files:
+        try:
+            df_tmp = pd.read_json(f, orient="records")
+        except Exception as err:
+            raise ValueError(f"Failed to read {f}") from err
+        cols_per_file.append(set(df_tmp.columns))
+
+    key_cols = [c for c in info_cols if all(c in cset for cset in cols_per_file)]
+    if not key_cols:
+        # soft fallback: use any info_cols present in the first file
+        key_cols = [c for c in info_cols if c in list(cols_per_file[0])]
+    if not key_cols:
+        raise ValueError(
+            "No common key columns found from info_cols across the input files."
+        )
+
+    # 2) build a single "meta" block (keys as columns) once, aligned by the key index
+    meta_added = False
+
+    for file in files:
+        df = pd.read_json(file, orient="records")
+
+        # Keep rows that actually have the compared metric (same as original behavior)
+        if drop_column in df.columns:
+            df = df.dropna(subset=[drop_column], ignore_index=True)
+
+        # Stabilize numeric key columns (harmless if missing)
+        for c in (
+            "Input Len",
+            "Output Len",
+            "TP Size",
+            "PP Size",
+            "# of max concurrency.",
+            "qps",
+        ):
+            if c in df.columns:
+                df[c] = pd.to_numeric(df[c], errors="coerce")
+
+        # Ensure all key columns exist
+        for c in key_cols:
+            if c not in df.columns:
+                df[c] = pd.NA
+
+        # Set index = key_cols and aggregate duplicates → unique MultiIndex
+        df_idx = df.set_index(key_cols, drop=False)
+
+        # meta (key columns), unique per key
+        meta = df_idx[key_cols]
+        if not meta.index.is_unique:
+            meta = meta.groupby(level=key_cols, dropna=False).first()
+
+        # metric series for this file, aggregated to one row per key
+        file_label = "/".join(file.split("/")[:-1]) or os.path.basename(file)
+        s = df_idx[data_column]
+        if not s.index.is_unique:
+            s = s.groupby(level=key_cols, dropna=False).mean()
+        s.name = file_label  # column label like original
+
+        # add meta once (from first file) so keys are the leftmost columns
+        if not meta_added:
+            frames.append(meta)
+            meta_added = True
+
+        # (NEW) debug: aligned test-name column per file
+        if debug and name_column in df_idx.columns:
+            name_s = df_idx[name_column]
+            if not name_s.index.is_unique:
+                name_s = name_s.groupby(level=key_cols, dropna=False).first()
+            name_s.name = f"{file_label}_name"
+            frames.append(name_s)
+
+        frames.append(s)
+        raw_data_cols.append(file_label)
+        compare_frames.append(s)
+
+        # Generalize ratio: for any file N>=2, add ratio (fileN / file1)
+        if len(compare_frames) >= 2:
+            base = compare_frames[0]
+            current = compare_frames[-1]
+            ratio = current / base
+            ratio = ratio.mask(base == 0)  # avoid inf when baseline is 0
+            ratio.name = f"Ratio 1 vs {len(compare_frames)}"
+            frames.append(ratio)
+
+    # 4) concat on columns with aligned MultiIndex;
+    # then reset_index to return keys as columns
    concat_df = pd.concat(frames, axis=1)
-    return concat_df
+    concat_df = concat_df.reset_index(drop=True).reset_index()
+    if "index" in concat_df.columns:
+        concat_df = concat_df.drop(columns=["index"])
+
+    # Ensure key/info columns appear first (in your info_cols order)
+    front = [c for c in info_cols if c in concat_df.columns]
+    rest = [c for c in concat_df.columns if c not in front]
+    concat_df = concat_df[front + rest]
+
+    print(raw_data_cols)
+    return concat_df, raw_data_cols
+
+
+def split_json_by_tp_pp(
+    input_file: str = "benchmark_results.json", output_root: str = "."
+) -> list[str]:
+    """
+    Split a benchmark JSON into separate folders by (TP Size, PP Size).
+
+    Creates: <output_root>/tp{TP}_pp{PP}/benchmark_results.json
+    Returns: list of file paths written.
+    """
+    # Load JSON data into DataFrame
+    with open(input_file, encoding="utf-8") as f:
+        data = json.load(f)
+
+    # If the JSON is a dict with a list under common keys, use that list
+    if isinstance(data, dict):
+        for key in ("results", "serving_results", "benchmarks", "data"):
+            if isinstance(data.get(key), list):
+                data = data[key]
+                break
+
+    df = pd.DataFrame(data)
+
+    # Keep only "serving" tests
+    name_col = next(
+        (c for c in ["Test name", "test_name", "Test Name"] if c in df.columns), None
+    )
+    if name_col:
+        df = df[
+            df[name_col].astype(str).str.contains(r"serving", case=False, na=False)
+        ].copy()
+
+    # Handle alias column names
+    rename_map = {
+        "tp_size": "TP Size",
+        "tensor_parallel_size": "TP Size",
+        "pp_size": "PP Size",
+        "pipeline_parallel_size": "PP Size",
+    }
+    df.rename(
+        columns={k: v for k, v in rename_map.items() if k in df.columns}, inplace=True
+    )
+
+    # Ensure TP/PP columns exist (default to 1 if missing)
+    if "TP Size" not in df.columns:
+        df["TP Size"] = 1
+    if "PP Size" not in df.columns:
+        df["PP Size"] = 1
+
+    # make sure TP/PP are numeric ints with no NaN
+    df["TP Size"] = (
+        pd.to_numeric(df.get("TP Size", 1), errors="coerce").fillna(1).astype(int)
+    )
+    df["PP Size"] = (
+        pd.to_numeric(df.get("PP Size", 1), errors="coerce").fillna(1).astype(int)
+    )
+
+    # Split into separate folders
+    saved_paths: list[str] = []
+    for (tp, pp), group_df in df.groupby(["TP Size", "PP Size"], dropna=False):
+        folder_name = os.path.join(output_root, f"tp{int(tp)}_pp{int(pp)}")
+        os.makedirs(folder_name, exist_ok=True)
+        filepath = os.path.join(folder_name, "benchmark_results.json")
+        group_df.to_json(filepath, orient="records", indent=2, force_ascii=False)
+        print(f"Saved: {filepath}")
+        saved_paths.append(filepath)
+
+    return saved_paths


 if __name__ == "__main__":
@ -36,31 +205,103 @@ if __name__ == "__main__":
        "-f", "--file", action="append", type=str, help="input file name"
    )
    parser.add_argument(
-        "--ignore_test_name", action="store_true", help="ignore_test_name or not"
+        "--debug", action="store_true", help="show all information for debugging"
+    )
+    parser.add_argument(
+        "--plot",
+        action=argparse.BooleanOptionalAction,
+        default=True,
+        help="plot perf diagrams or not --no-plot --plot",
+    )
+    parser.add_argument(
+        "-x",
+        "--xaxis",
+        type=str,
+        default="# of max concurrency.",
+        help="column name to use as X Axis in comparision graph",
    )
    args = parser.parse_args()
-    files = args.file
-    print("comparing : " + ", ".join(files))

    drop_column = "P99"
    name_column = "Test name"
+    info_cols = [
+        "Model",
+        "Dataset Name",
+        "Input Len",
+        "Output Len",
+        "TP Size",
+        "PP Size",
+        "# of max concurrency.",
+        "qps",
+    ]
    data_cols_to_compare = ["Output Tput (tok/s)", "Median TTFT (ms)", "Median"]
    html_msgs_for_data_cols = [
        "Compare Output Tokens /n",
        "Median TTFT /n",
        "Median TPOT /n",
    ]
-    ignore_test_name = args.ignore_test_name
+
+    if len(args.file) == 1:
+        files = split_json_by_tp_pp(args.file[0], output_root="splits")
+        info_cols = [c for c in info_cols if c not in ("TP Size", "PP Size")]
+    else:
+        files = args.file
+    print("comparing : " + ", ".join(files))
+    debug = args.debug
+    plot = args.plot
+    # For Plot feature, assign y axis from one of info_cols
+    y_axis_index = info_cols.index(args.xaxis) if args.xaxis in info_cols else 6
    with open("perf_comparison.html", "w") as text_file:
        for i in range(len(data_cols_to_compare)):
-            output_df = compare_data_columns(
+            output_df, raw_data_cols = compare_data_columns(
                files,
                name_column,
                data_cols_to_compare[i],
+                info_cols,
                drop_column,
-                ignore_test_name=ignore_test_name,
+                debug=debug,
            )
-            print(output_df)
-            html = output_df.to_html()
-            text_file.write(html_msgs_for_data_cols[i])
-            text_file.write(html)
+
+            # For Plot feature, insert y axis from one of info_cols
+            raw_data_cols.insert(0, info_cols[y_axis_index])
+
+            filtered_info_cols = info_cols[:-2]
+            existing_group_cols = [
+                c for c in filtered_info_cols if c in output_df.columns
+            ]
+            if not existing_group_cols:
+                raise ValueError(
+                    f"No valid group-by columns  "
+                    f"Expected subset: {filtered_info_cols}, "
+                    f"but DataFrame has: {list(output_df.columns)}"
+                )
+            output_df_sorted = output_df.sort_values(by=existing_group_cols)
+            output_groups = output_df_sorted.groupby(existing_group_cols, dropna=False)
+            for name, group in output_groups:
+                html = group.to_html()
+                text_file.write(html_msgs_for_data_cols[i])
+                text_file.write(html)
+
+                if plot and plotly_found:
+                    import plotly.express as px
+
+                    df = group[raw_data_cols]
+                    df_sorted = df.sort_values(by=info_cols[y_axis_index])
+                    # Melt DataFrame for plotting
+                    df_melted = df_sorted.melt(
+                        id_vars=info_cols[y_axis_index],
+                        var_name="Configuration",
+                        value_name=data_cols_to_compare[i],
+                    )
+                    title = data_cols_to_compare[i] + " vs " + info_cols[y_axis_index]
+                    # Create Plotly line chart
+                    fig = px.line(
+                        df_melted,
+                        x=info_cols[y_axis_index],
+                        y=data_cols_to_compare[i],
+                        color="Configuration",
+                        title=title,
+                        markers=True,
+                    )
+                    # Export to HTML
+                    text_file.write(fig.to_html(full_html=True, include_plotlyjs="cdn"))
--- a/.buildkite/nightly-benchmarks/scripts/convert-results-json-to-markdown.py
+++ b/.buildkite/nightly-benchmarks/scripts/convert-results-json-to-markdown.py
@ -1,17 +1,19 @@
 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project

+import argparse
 import json
 import os
+import shlex
 from importlib import util
 from pathlib import Path
+from typing import Any

 import pandas as pd
 import psutil
+import regex as re
 from tabulate import tabulate

-results_folder = Path("results/")
-
 # latency results and the keys that will be printed into markdown
 latency_results = []
 latency_column_mapping = {
@ -42,13 +44,22 @@ throughput_results_column_mapping = {
 serving_results = []
 serving_column_mapping = {
    "test_name": "Test name",
+    "model_id": "Model",
+    "dataset_name": "Dataset Name",
+    "input_len": "Input Len",
+    "output_len": "Output Len",
+    "tp_size": "TP Size",
+    "pp_size": "PP Size",
+    "dtype": "dtype",
    "gpu_type": "GPU",
    "completed": "# of req.",
+    "qps": "qps",
+    "max_concurrency": "# of max concurrency.",
    "request_throughput": "Tput (req/s)",
    "total_token_throughput": "Total Token Tput (tok/s)",
    "output_throughput": "Output Tput (tok/s)",
-    "total_input_tokens": "Total input tokens",
-    "total_output_tokens": "Total output tokens",
+    # "total_input_tokens": "Total input tokens",
+    # "total_output_tokens": "Total output tokens",
    "mean_ttft_ms": "Mean TTFT (ms)",
    "median_ttft_ms": "Median TTFT (ms)",
    "p99_ttft_ms": "P99 TTFT (ms)",
@ -93,15 +104,111 @@ def get_size_with_unit(bytes, suffix="B"):
        bytes /= factor


+def _coerce(val: str) -> Any:
+    """Best-effort type coercion from string to Python types."""
+    low = val.lower()
+    if low == "null":
+        return None
+    if low == "true":
+        return True
+    if low == "false":
+        return False
+    # integers
+    if re.fullmatch(r"[+-]?\d+", val):
+        try:
+            return int(val)
+        except ValueError:
+            pass
+    # floats (keep 'inf'/'-inf'/'nan' as strings)
+    if re.fullmatch(r"[+-]?\d*\.\d+", val):
+        try:
+            return float(val)
+        except ValueError:
+            pass
+    return val
+
+
+def parse_client_command(cmd: str) -> dict[str, Any]:
+    """Parse the client_command shell string into {executable, script, args}."""
+    toks = shlex.split(cmd)
+    if len(toks) < 2:
+        raise ValueError("client_command must include an executable and a script")
+    executable, script = toks[0], toks[1]
+    args: dict[str, Any] = {}
+
+    i = 2
+    while i < len(toks):
+        t = toks[i]
+        if t.startswith("--"):
+            # --key=value or --key (value) or boolean flag
+            if "=" in t:
+                key, val = t.split("=", 1)
+                if key == "--metadata":
+                    md = {}
+                    if val:
+                        if "=" in val:
+                            k, v = val.split("=", 1)
+                            md[k] = _coerce(v)
+                        else:
+                            md[val] = True
+                    args[key] = md
+                else:
+                    args[key] = _coerce(val)
+                i += 1
+                continue
+
+            key = t
+
+            # Special: consume metadata k=v pairs until next --flag
+            if key == "--metadata":
+                i += 1
+                md = {}
+                while i < len(toks) and not toks[i].startswith("--"):
+                    pair = toks[i]
+                    if "=" in pair:
+                        k, v = pair.split("=", 1)
+                        md[k] = _coerce(v)
+                    else:
+                        md[pair] = True
+                    i += 1
+                args[key] = md
+                continue
+
+            # Standard: check if next token is a value (not a flag)
+            if i + 1 < len(toks) and not toks[i + 1].startswith("--"):
+                args[key] = _coerce(toks[i + 1])
+                i += 2
+            else:
+                # lone flag -> True
+                args[key] = True
+                i += 1
+        else:
+            # unexpected positional; skip
+            i += 1
+
+    return {"executable": executable, "script": script, "args": args}
+
+
 if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "-r",
+        "--result",
+        type=str,
+        default="results",
+        help="Folder name for benchmark output results.",
+    )
+    args = parser.parse_args()
+    results_folder = Path(args.result)
+    if not results_folder.exists():
+        raise FileNotFoundError(f"results folder does not exist: {results_folder}")
    # collect results
    for test_file in results_folder.glob("*.json"):
        with open(test_file) as f:
            raw_result = json.loads(f.read())

        if "serving" in str(test_file):
-            # this result is generated via `benchmark_serving.py`
-
+            # this result is generated via `vllm bench serve` command
            # attach the benchmarking command to raw_result
            try:
                with open(test_file.with_suffix(".commands")) as f:
@ -109,18 +216,50 @@ if __name__ == "__main__":
            except OSError as e:
                print(e)
                continue
+            # Parse Server Command Arg
+            out: dict[str, Any] = {
+                "server_command": parse_client_command(command["server_command"])
+            }
+            parse_args = [
+                "--tensor-parallel-size",
+                "--pipeline-parallel-size",
+                "--dtype",
+            ]
+            col_mapping = ["tp_size", "pp_size", "dtype"]
+            for index, arg in enumerate(parse_args):
+                if arg in out["server_command"]["args"]:
+                    raw_result.update(
+                        {col_mapping[index]: out["server_command"]["args"][arg]}
+                    )

+            # Parse Client Command Arg
+            out: dict[str, Any] = {
+                "client_command": parse_client_command(command["client_command"])
+            }
+            parse_args = [
+                "--dataset-name",
+                "--random-input-len",
+                "--random-output-len",
+                "--request-rate",
+            ]
+            col_mapping = ["dataset_name", "input_len", "output_len", "qps"]
+
+            for index, arg in enumerate(parse_args):
+                if arg in out["client_command"]["args"]:
+                    raw_result.update(
+                        {col_mapping[index]: out["client_command"]["args"][arg]}
+                    )
+            # Add Server, Client command
            raw_result.update(command)

            # update the test name of this result
            raw_result.update({"test_name": test_file.stem})
-
            # add the result to raw_result
            serving_results.append(raw_result)
            continue

        elif "latency" in f.name:
-            # this result is generated via `benchmark_latency.py`
+            # this result is generated via `vllm bench latency` command

            # attach the benchmarking command to raw_result
            try:
@ -148,7 +287,7 @@ if __name__ == "__main__":
            continue

        elif "throughput" in f.name:
-            # this result is generated via `benchmark_throughput.py`
+            # this result is generated via `vllm bench throughput` command

            # attach the benchmarking command to raw_result
            try:
@ -204,7 +343,10 @@ if __name__ == "__main__":
            columns=latency_column_mapping
        )
    if not serving_results.empty:
-        serving_results = serving_results[list(serving_column_mapping.keys())].rename(
+        valid_columns = [
+            col for col in serving_column_mapping if col in serving_results.columns
+        ]
+        serving_results = serving_results[valid_columns].rename(
            columns=serving_column_mapping
        )
    if not throughput_results.empty:
@ -244,7 +386,9 @@ if __name__ == "__main__":
    )

    # document the result
-    with open(results_folder / "benchmark_results.md", "w") as f:
+    md_file = "benchmark_results.md"
+    json_file = "benchmark_results.json"
+    with open(results_folder / md_file, "w") as f:
        results = read_markdown(
            "../.buildkite/nightly-benchmarks/"
            + "performance-benchmarks-descriptions.md"
@ -259,7 +403,7 @@ if __name__ == "__main__":
        f.write(results)

    # document benchmarking results in json
-    with open(results_folder / "benchmark_results.json", "w") as f:
+    with open(results_folder / json_file, "w") as f:
        results = (
            latency_results.to_dict(orient="records")
            + throughput_results.to_dict(orient="records")
--- a/.buildkite/nightly-benchmarks/scripts/run-nightly-benchmarks.sh
+++ b/.buildkite/nightly-benchmarks/scripts/run-nightly-benchmarks.sh
@ -73,7 +73,7 @@ get_current_llm_serving_engine() {
    echo "Container: vllm"
    # move to a completely irrelevant directory, to avoid import vllm from current folder
    export CURRENT_LLM_SERVING_ENGINE=vllm
-    
+
    return
  fi
 }
@ -95,12 +95,14 @@ json2args() {
 }

 kill_gpu_processes() {
-  pkill -f python
-  pkill -f python3
-  pkill -f tritonserver
-  pkill -f pt_main_thread
-  pkill -f text-generation
-  pkill -f lmdeploy
+  pkill -f '[p]ython'
+  pkill -f '[p]ython3'
+  pkill -f '[t]ritonserver'
+  pkill -f '[p]t_main_thread'
+  pkill -f '[t]ext-generation'
+  pkill -f '[l]mdeploy'
+  # vLLM now names the process with VLLM prefix after https://github.com/vllm-project/vllm/pull/21445
+  pkill -f '[V]LLM'

  while [ "$(nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits | head -n 1)" -ge 1000 ]; do
    sleep 1
@ -125,7 +127,7 @@ ensure_installed() {
 }

 run_serving_tests() {
-  # run serving tests using `benchmark_serving.py`
+  # run serving tests using `vllm bench serve` command
  # $1: a json file specifying serving test cases

  local serving_test_file
@ -225,7 +227,7 @@ run_serving_tests() {

      if [[ "$dataset_name" = "sharegpt" ]]; then

-        client_command="python3 benchmark_serving.py \
+        client_command="vllm bench serve \
          --backend $backend \
          --tokenizer /tokenizer_cache \
          --model $model \
@ -246,7 +248,7 @@ run_serving_tests() {
        sonnet_output_len=$(echo "$common_params" | jq -r '.sonnet_output_len')
        sonnet_prefix_len=$(echo "$common_params" | jq -r '.sonnet_prefix_len')

-        client_command="python3 benchmark_serving.py \
+        client_command="vllm bench serve \
          --backend $backend \
          --tokenizer /tokenizer_cache \
          --model $model \
@ -265,13 +267,13 @@ run_serving_tests() {
          $client_args"

      else
-  
+
        echo "The dataset name must be either 'sharegpt' or 'sonnet'. Got $dataset_name."
        exit 1

      fi

-        
+

      echo "Running test case $test_name with qps $qps"
      echo "Client command: $client_command"
@ -302,7 +304,7 @@ run_serving_tests() {
 }

 run_genai_perf_tests() {
-  # run genai-perf tests 
+  # run genai-perf tests

  # $1: a json file specifying genai-perf test cases
  local genai_perf_test_file
@ -311,14 +313,14 @@ run_genai_perf_tests() {
  # Iterate over genai-perf tests
  jq -c '.[]' "$genai_perf_test_file" | while read -r params; do
    # get the test name, and append the GPU type back to it.
-    test_name=$(echo "$params" | jq -r '.test_name')    
-    
+    test_name=$(echo "$params" | jq -r '.test_name')
+
    # if TEST_SELECTOR is set, only run the test cases that match the selector
    if [[ -n "$TEST_SELECTOR" ]] && [[ ! "$test_name" =~ $TEST_SELECTOR ]]; then
      echo "Skip test case $test_name."
      continue
    fi
-    
+
    # prepend the current serving engine to the test name
    test_name=${CURRENT_LLM_SERVING_ENGINE}_${test_name}

@ -369,10 +371,10 @@ run_genai_perf_tests() {
        qps=$num_prompts
        echo "now qps is $qps"
      fi
-    
+
      new_test_name=$test_name"_qps_"$qps
      backend=$CURRENT_LLM_SERVING_ENGINE
-      
+
      if [[ "$backend" == *"vllm"* ]]; then
        backend="vllm"
      fi
@ -413,7 +415,7 @@ prepare_dataset() {
  do
    cat sonnet.txt >> sonnet_4x.txt
  done
-  
+
 }

 main() {
--- a/.buildkite/nightly-benchmarks/scripts/run-performance-benchmarks.sh
+++ b/.buildkite/nightly-benchmarks/scripts/run-performance-benchmarks.sh
@ -33,7 +33,7 @@ check_gpus() {

 check_cpus() {
  # check the number of CPUs and NUMA Node and GPU type.
-  declare -g numa_count=$(python3 -c  "from numa import info;numa_size = info.get_num_configured_nodes(); print(numa_size)")
+  declare -g numa_count=$(lscpu | grep "NUMA node(s):" | awk '{print $3}')
  if [[ $numa_count -gt 0 ]]; then
    echo "NUMA found."
    echo $numa_count
@ -126,7 +126,8 @@ kill_gpu_processes() {
  ps -aux
  lsof -t -i:8000 | xargs -r kill -9
  pgrep python3 | xargs -r kill -9
-
+  # vLLM now names the process with VLLM prefix after https://github.com/vllm-project/vllm/pull/21445
+  pgrep VLLM | xargs -r kill -9

  # wait until GPU memory usage smaller than 1GB
  if command -v nvidia-smi; then
@ -164,7 +165,7 @@ upload_to_buildkite() {
 }

 run_latency_tests() {
-  # run latency tests using `benchmark_latency.py`
+  # run latency tests using `vllm bench latency` command
  # $1: a json file specifying latency test cases

  local latency_test_file
@ -193,9 +194,11 @@ run_latency_tests() {

    # check if there is enough GPU to run the test
    tp=$(echo "$latency_params" | jq -r '.tensor_parallel_size')
-    if [ "$ON_CPU" == "1" ];then
-      if [[ $numa_count -lt $tp ]]; then
-        echo "Required tensor-parallel-size $tp but only $numa_count NUMA nodes found. Skip testcase $test_name."
+    if [ "$ON_CPU" == "1" ]; then
+      pp=$(echo "$latency_params" | jq -r '.pipeline_parallel_size')
+      world_size=$(($tp*$pp))
+      if [[ $numa_count -lt $world_size  && -z "${REMOTE_HOST}" ]]; then
+        echo "Required world-size $world_size but only $numa_count NUMA nodes found. Skip testcase $test_name."
        continue
      fi
    else
@ -205,7 +208,7 @@ run_latency_tests() {
      fi
    fi

-    latency_command=" $latency_envs python3 benchmark_latency.py \
+    latency_command=" $latency_envs vllm bench latency \
      --output-json $RESULTS_FOLDER/${test_name}.json \
      $latency_args"

@ -231,7 +234,7 @@ run_latency_tests() {
 }

 run_throughput_tests() {
-  # run throughput tests using `benchmark_throughput.py`
+  # run throughput tests using `vllm bench throughput`
  # $1: a json file specifying throughput test cases

  local throughput_test_file
@ -260,9 +263,11 @@ run_throughput_tests() {

    # check if there is enough GPU to run the test
    tp=$(echo "$throughput_params" | jq -r '.tensor_parallel_size')
-    if [ "$ON_CPU" == "1" ];then
-      if [[ $numa_count -lt $tp ]]; then
-        echo "Required tensor-parallel-size $tp but only $numa_count NUMA nodes found. Skip testcase $test_name."
+    if [ "$ON_CPU" == "1" ]; then
+      pp=$(echo "$throughput_params" | jq -r '.pipeline_parallel_size')
+      world_size=$(($tp*$pp))
+      if [[ $numa_count -lt $world_size  && -z "${REMOTE_HOST}" ]]; then
+        echo "Required world-size $world_size but only $numa_count NUMA nodes found. Skip testcase $test_name."
        continue
      fi
    else
@ -272,7 +277,7 @@ run_throughput_tests() {
      fi
    fi

-    throughput_command=" $throughput_envs python3 benchmark_throughput.py \
+    throughput_command=" $throughput_envs vllm bench throughput \
      --output-json $RESULTS_FOLDER/${test_name}.json \
      $throughput_args"

@ -297,7 +302,7 @@ run_throughput_tests() {
 }

 run_serving_tests() {
-  # run serving tests using `benchmark_serving.py`
+  # run serving tests using `vllm bench serve` command
  # $1: a json file specifying serving test cases

  local serving_test_file
@ -328,12 +333,21 @@ run_serving_tests() {
    qps_list=$(echo "$params" | jq -r '.qps_list')
    qps_list=$(echo "$qps_list" | jq -r '.[] | @sh')
    echo "Running over qps list $qps_list"
+    max_concurrency_list=$(echo "$params" | jq -r '.max_concurrency_list')
+    if [[ -z "$max_concurrency_list" || "$max_concurrency_list" == "null" ]]; then
+        num_prompts=$(echo "$client_params" | jq -r '.num_prompts')
+        max_concurrency_list="[$num_prompts]"
+    fi
+    max_concurrency_list=$(echo "$max_concurrency_list" | jq -r '.[] | @sh')
+    echo "Running over max concurrency list $max_concurrency_list"

    # check if there is enough resources to run the test
    tp=$(echo "$server_params" | jq -r '.tensor_parallel_size')
-    if [ "$ON_CPU" == "1" ];then
-      if [[ $numa_count -lt $tp ]]; then
-        echo "Required tensor-parallel-size $tp but only $numa_count NUMA nodes found. Skip testcase $test_name."
+    if [ "$ON_CPU" == "1" ]; then
+      pp=$(echo "$server_params" | jq -r '.pipeline_parallel_size')
+      world_size=$(($tp*$pp))
+      if [[ $numa_count -lt $world_size  && -z "${REMOTE_HOST}" ]]; then
+        echo "Required world-size $world_size but only $numa_count NUMA nodes found. Skip testcase $test_name."
        continue
      fi
    else
@ -389,35 +403,39 @@ run_serving_tests() {
        echo "now qps is $qps"
      fi

-      new_test_name=$test_name"_qps_"$qps
+      # iterate over different max_concurrency
+      for max_concurrency in $max_concurrency_list; do
+        new_test_name=$test_name"_qps_"$qps"_concurrency_"$max_concurrency
+        echo " new test name $new_test_name"
+        # pass the tensor parallel size to the client so that it can be displayed
+        # on the benchmark dashboard
+        client_command="vllm bench serve \
+          --save-result \
+          --result-dir $RESULTS_FOLDER \
+          --result-filename ${new_test_name}.json \
+          --request-rate $qps \
+          --max-concurrency $max_concurrency \
+          --metadata "tensor_parallel_size=$tp" \
+          $client_args $client_remote_args "

-      # pass the tensor parallel size to the client so that it can be displayed
-      # on the benchmark dashboard
-      client_command="python3 benchmark_serving.py \
-        --save-result \
-        --result-dir $RESULTS_FOLDER \
-        --result-filename ${new_test_name}.json \
-        --request-rate $qps \
-        --metadata "tensor_parallel_size=$tp" \
-        $client_args $client_remote_args "
+        echo "Running test case $test_name with qps $qps"
+        echo "Client command: $client_command"

-      echo "Running test case $test_name with qps $qps"
-      echo "Client command: $client_command"
+        bash -c "$client_command"

-      bash -c "$client_command"
-
-      # record the benchmarking commands
-      jq_output=$(jq -n \
-        --arg server "$server_command" \
-        --arg client "$client_command" \
-        --arg gpu "$gpu_type" \
-        '{
-          server_command: $server,
-          client_command: $client,
-          gpu_type: $gpu
-        }')
-      echo "$jq_output" >"$RESULTS_FOLDER/${new_test_name}.commands"
+        # record the benchmarking commands
+        jq_output=$(jq -n \
+          --arg server "$server_command" \
+          --arg client "$client_command" \
+          --arg gpu "$gpu_type" \
+          '{
+            server_command: $server,
+            client_command: $client,
+            gpu_type: $gpu
+          }')
+        echo "$jq_output" >"$RESULTS_FOLDER/${new_test_name}.commands"

+      done
    done

    # clean up
@ -447,7 +465,7 @@ main() {
  (which jq) || (apt-get update && apt-get -y install jq)
  (which lsof) || (apt-get update && apt-get install -y lsof)

-  # get the current IP address, required by benchmark_serving.py
+  # get the current IP address, required by `vllm bench serve` command
  export VLLM_HOST_IP=$(hostname -I | awk '{print $1}')
  # turn of the reporting of the status of each request, to clean up the terminal output
  export VLLM_LOGGING_LEVEL="WARNING"
--- a/.buildkite/nightly-benchmarks/tests/genai-perf-tests.json
+++ b/.buildkite/nightly-benchmarks/tests/genai-perf-tests.json
@ -11,9 +11,7 @@
        },
        "vllm_server_parameters": {
            "disable_log_stats": "",
-            "disable_log_requests": "",
            "gpu_memory_utilization": 0.9,
-            "num_scheduler_steps": 10,
            "max_num_seqs": 512,
            "dtype": "bfloat16"
        },
--- a/.buildkite/nightly-benchmarks/tests/latency-tests-cpu.json
+++ b/.buildkite/nightly-benchmarks/tests/latency-tests-cpu.json
@ -6,7 +6,7 @@
 	    "VLLM_CPU_KVCACHE_SPACE": 40
        },
        "parameters": {
-            "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "tensor_parallel_size": 1,
            "load_format": "dummy",
            "num_iters_warmup": 5,
@ -20,7 +20,7 @@
 	    "VLLM_CPU_KVCACHE_SPACE": 40
        },
        "parameters": {
-            "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "tensor_parallel_size": 4,
            "load_format": "dummy",
            "num_iters_warmup": 5,
--- a/.buildkite/nightly-benchmarks/tests/nightly-tests.json
+++ b/.buildkite/nightly-benchmarks/tests/nightly-tests.json
@ -35,9 +35,7 @@
        }, 
        "vllm_server_parameters": {
            "disable_log_stats": "",
-            "disable_log_requests": "",
            "gpu_memory_utilization": 0.9,
-            "num_scheduler_steps": 10,
            "max_num_seqs": 512,
            "dtype": "bfloat16"
        },
@ -90,9 +88,7 @@
        }, 
        "vllm_server_parameters": {
            "disable_log_stats": "",
-            "disable_log_requests": "",
            "gpu_memory_utilization": 0.9,
-            "num_scheduler_steps": 10,
            "max_num_seqs": 512,
            "dtype": "bfloat16"
        },
@ -145,9 +141,7 @@
        }, 
        "vllm_server_parameters": {
            "disable_log_stats": "",
-            "disable_log_requests": "",
            "gpu_memory_utilization": 0.9,
-            "num_scheduler_steps": 10,
            "max_num_seqs": 512,
            "dtype": "bfloat16"
        },
@ -197,9 +191,7 @@
        }, 
        "vllm_server_parameters": {
            "disable_log_stats": "",
-            "disable_log_requests": "",
            "gpu_memory_utilization": 0.9,
-            "num_scheduler_steps": 10,
            "max_num_seqs": 512,
            "dtype": "bfloat16"
        },
@ -251,9 +243,7 @@
        }, 
        "vllm_server_parameters": {
            "disable_log_stats": "",
-            "disable_log_requests": "",
            "gpu_memory_utilization": 0.9,
-            "num_scheduler_steps": 10,
            "max_num_seqs": 512,
            "dtype": "bfloat16"
        },
@ -305,9 +295,7 @@
        }, 
        "vllm_server_parameters": {
            "disable_log_stats": "",
-            "disable_log_requests": "",
            "gpu_memory_utilization": 0.9,
-            "num_scheduler_steps": 10,
            "max_num_seqs": 512,
            "dtype": "bfloat16"
        },
--- a/.buildkite/nightly-benchmarks/tests/serving-tests-cpu-snc2.json
+++ b/.buildkite/nightly-benchmarks/tests/serving-tests-cpu-snc2.json
@ -0,0 +1,202 @@
+[
+    {
+        "test_name": "serving_llama8B_tp1_sharegpt",
+        "qps_list": ["inf"],
+        "max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
+        "server_environment_variables": {
+            "VLLM_RPC_TIMEOUT": 100000,
+	    "VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
+	    "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
+	    "VLLM_CPU_SGL_KERNEL": 1,
+	    "VLLM_CPU_KVCACHE_SPACE": 40
+        },
+        "server_parameters": {
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
+            "tensor_parallel_size": 1,
+	    "dtype": "bfloat16",
+	    "distributed_executor_backend": "mp",
+	    "block_size": 128,
+	    "trust_remote_code": "",
+            "disable_log_stats": "",
+	    "enforce_eager": "",
+	    "max_num_batched_tokens": 2048,
+	    "max_num_seqs": 256,
+            "load_format": "dummy"
+        },
+        "client_parameters": {
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
+            "backend": "vllm",
+            "dataset_name": "sharegpt",
+            "dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
+            "num_prompts": 200
+        }
+    },
+    {
+        "test_name": "serving_llama8B_tp2_sharegpt",
+        "qps_list": ["inf"],
+        "max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
+        "server_environment_variables": {
+            "VLLM_RPC_TIMEOUT": 100000,
+	    "VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
+	    "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
+	    "VLLM_CPU_SGL_KERNEL": 1,
+	    "VLLM_CPU_KVCACHE_SPACE": 40
+        },
+        "server_parameters": {
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
+            "tensor_parallel_size": 2,
+	    "dtype": "bfloat16",
+	    "distributed_executor_backend": "mp",
+	    "block_size": 128,
+	    "trust_remote_code": "",
+            "disable_log_stats": "",
+	    "enforce_eager": "",
+	    "max_num_batched_tokens": 2048,
+	    "max_num_seqs": 256,
+            "load_format": "dummy"
+        },
+        "client_parameters": {
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
+            "backend": "vllm",
+            "dataset_name": "sharegpt",
+            "dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
+            "num_prompts": 200
+        }
+    },
+    {
+        "test_name": "serving_llama8B_tp4_sharegpt",
+        "qps_list": ["inf"],
+        "max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
+        "server_environment_variables": {
+            "VLLM_RPC_TIMEOUT": 100000,
+	    "VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
+	    "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
+	    "VLLM_CPU_SGL_KERNEL": 1,
+	    "VLLM_CPU_KVCACHE_SPACE": 40
+        },
+        "server_parameters": {
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
+            "tensor_parallel_size": 4,
+	    "dtype": "bfloat16",
+	    "distributed_executor_backend": "mp",
+	    "block_size": 128,
+	    "trust_remote_code": "",
+            "disable_log_stats": "",
+	    "enforce_eager": "",
+	    "max_num_batched_tokens": 2048,
+	    "max_num_seqs": 256,
+            "load_format": "dummy"
+        },
+        "client_parameters": {
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
+            "backend": "vllm",
+            "dataset_name": "sharegpt",
+            "dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
+            "num_prompts": 200
+        }
+    },
+    {
+        "test_name": "serving_llama8B_tp1_random_128_128",
+        "qps_list": ["inf"],
+        "max_concurrency_list": [12, 16, 24, 32, 64, 128, 200, 1000],
+        "server_environment_variables": {
+            "VLLM_RPC_TIMEOUT": 100000,
+	    "VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
+	    "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
+	    "VLLM_CPU_SGL_KERNEL": 1,
+	    "VLLM_CPU_KVCACHE_SPACE": 40
+        },
+        "server_parameters": {
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
+            "tensor_parallel_size": 1,
+	    "dtype": "bfloat16",
+	    "distributed_executor_backend": "mp",
+	    "block_size": 128,
+	    "trust_remote_code": "",
+	    "enable_chunked_prefill": "",
+            "disable_log_stats": "",
+	    "enforce_eager": "",
+	    "max_num_batched_tokens": 2048,
+	    "max_num_seqs": 256,
+            "load_format": "dummy"
+        },
+        "client_parameters": {
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
+            "backend": "vllm",
+            "dataset_name": "random",
+	    "random-input-len": 128,
+	    "random-output-len": 128,
+	    "ignore-eos": "",
+            "num_prompts": 1000
+        }
+    },
+    {
+        "test_name": "serving_llama8B_tp2_random_128_128",
+        "qps_list": ["inf"],
+        "max_concurrency_list": [12, 16, 24, 32, 64, 128, 200, 1000],
+        "server_environment_variables": {
+            "VLLM_RPC_TIMEOUT": 100000,
+	    "VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
+	    "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
+	    "VLLM_CPU_SGL_KERNEL": 1,
+	    "VLLM_CPU_KVCACHE_SPACE": 40
+        },
+        "server_parameters": {
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
+            "tensor_parallel_size": 2,
+	    "dtype": "bfloat16",
+	    "distributed_executor_backend": "mp",
+	    "block_size": 128,
+	    "trust_remote_code": "",
+	    "enable_chunked_prefill": "",
+            "disable_log_stats": "",
+	    "enforce_eager": "",
+	    "max_num_batched_tokens": 2048,
+	    "max_num_seqs": 256,
+            "load_format": "dummy"
+        },
+        "client_parameters": {
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
+            "backend": "vllm",
+            "dataset_name": "random",
+	    "random-input-len": 128,
+	    "random-output-len": 128,
+	    "ignore-eos": "",
+            "num_prompts": 1000
+        }
+    },
+    {
+        "test_name": "serving_llama8B_tp4_random_128_128",
+        "qps_list": ["inf"],
+        "max_concurrency_list": [12, 16, 24, 32, 64, 128, 200, 1000],
+        "server_environment_variables": {
+            "VLLM_RPC_TIMEOUT": 100000,
+	    "VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
+	    "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
+	    "VLLM_CPU_SGL_KERNEL": 1,
+	    "VLLM_CPU_KVCACHE_SPACE": 40
+        },
+        "server_parameters": {
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
+            "tensor_parallel_size": 4,
+	    "dtype": "bfloat16",
+	    "distributed_executor_backend": "mp",
+	    "block_size": 128,
+	    "trust_remote_code": "",
+	    "enable_chunked_prefill": "",
+            "disable_log_stats": "",
+	    "enforce_eager": "",
+	    "max_num_batched_tokens": 2048,
+	    "max_num_seqs": 256,
+            "load_format": "dummy"
+        },
+        "client_parameters": {
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
+            "backend": "vllm",
+            "dataset_name": "random",
+	    "random-input-len": 128,
+	    "random-output-len": 128,
+            "num_prompts": 1000
+        }
+    }
+]
--- a/.buildkite/nightly-benchmarks/tests/serving-tests-cpu-snc3.json
+++ b/.buildkite/nightly-benchmarks/tests/serving-tests-cpu-snc3.json
@ -0,0 +1,205 @@
+[
+    {
+        "test_name": "serving_llama8B_pp1_sharegpt",
+        "qps_list": ["inf"],
+        "max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
+        "server_environment_variables": {
+            "VLLM_RPC_TIMEOUT": 100000,
+	    "VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
+	    "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
+	    "VLLM_CPU_SGL_KERNEL": 1,
+	    "VLLM_CPU_KVCACHE_SPACE": 40
+        },
+        "server_parameters": {
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
+            "pipeline_parallel_size": 1,
+	    "dtype": "bfloat16",
+	    "distributed_executor_backend": "mp",
+	    "block_size": 128,
+	    "trust_remote_code": "",
+            "disable_log_stats": "",
+	    "enforce_eager": "",
+	    "max_num_batched_tokens": 2048,
+	    "max_num_seqs": 256,
+            "load_format": "dummy"
+        },
+        "client_parameters": {
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
+            "backend": "vllm",
+            "dataset_name": "sharegpt",
+            "dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
+            "num_prompts": 200
+        }
+    },
+    {
+        "test_name": "serving_llama8B_pp3_sharegpt",
+        "qps_list": ["inf"],
+        "max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
+        "server_environment_variables": {
+            "VLLM_RPC_TIMEOUT": 100000,
+	    "VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
+	    "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
+	    "VLLM_CPU_SGL_KERNEL": 1,
+	    "VLLM_CPU_KVCACHE_SPACE": 40
+        },
+        "server_parameters": {
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
+            "pipeline_parallel_size": 3,
+	    "dtype": "bfloat16",
+	    "distributed_executor_backend": "mp",
+	    "block_size": 128,
+	    "trust_remote_code": "",
+            "disable_log_stats": "",
+	    "enforce_eager": "",
+	    "max_num_batched_tokens": 2048,
+	    "max_num_seqs": 256,
+            "load_format": "dummy"
+        },
+        "client_parameters": {
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
+            "backend": "vllm",
+            "dataset_name": "sharegpt",
+            "dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
+            "num_prompts": 200
+        }
+    },
+    {
+        "test_name": "serving_llama8B_tp2pp3_sharegpt",
+        "qps_list": ["inf"],
+        "max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
+        "server_environment_variables": {
+            "VLLM_RPC_TIMEOUT": 100000,
+	    "VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
+	    "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
+	    "VLLM_CPU_SGL_KERNEL": 1,
+	    "VLLM_CPU_KVCACHE_SPACE": 40
+        },
+        "server_parameters": {
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
+            "tensor_parallel_size": 2,
+            "pipeline_parallel_size": 3,
+	    "dtype": "bfloat16",
+	    "distributed_executor_backend": "mp",
+	    "block_size": 128,
+	    "trust_remote_code": "",
+            "disable_log_stats": "",
+	    "enforce_eager": "",
+	    "max_num_batched_tokens": 2048,
+	    "max_num_seqs": 256,
+            "load_format": "dummy"
+        },
+        "client_parameters": {
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
+            "backend": "vllm",
+            "dataset_name": "sharegpt",
+            "dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
+            "num_prompts": 200
+        }
+    },
+    {
+        "test_name": "serving_llama8B_pp1_random_128_128",
+        "qps_list": ["inf"],
+        "max_concurrency_list": [12, 16, 24, 32, 64, 128, 200, 1000],
+        "server_environment_variables": {
+            "VLLM_RPC_TIMEOUT": 100000,
+	    "VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
+	    "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
+	    "VLLM_CPU_SGL_KERNEL": 1,
+	    "VLLM_CPU_KVCACHE_SPACE": 40
+        },
+        "server_parameters": {
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
+            "pipeline_parallel_size": 1,
+	    "dtype": "bfloat16",
+	    "distributed_executor_backend": "mp",
+	    "block_size": 128,
+	    "trust_remote_code": "",
+	    "enable_chunked_prefill": "",
+            "disable_log_stats": "",
+	    "enforce_eager": "",
+	    "max_num_batched_tokens": 2048,
+	    "max_num_seqs": 256,
+            "load_format": "dummy"
+        },
+        "client_parameters": {
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
+            "backend": "vllm",
+            "dataset_name": "random",
+	    "random-input-len": 128,
+	    "random-output-len": 128,
+	    "ignore-eos": "",
+            "num_prompts": 1000
+        }
+    },
+    {
+        "test_name": "serving_llama8B_pp3_random_128_128",
+        "qps_list": ["inf"],
+        "max_concurrency_list": [12, 16, 24, 32, 64, 128, 200, 1000],
+        "server_environment_variables": {
+            "VLLM_RPC_TIMEOUT": 100000,
+	    "VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
+	    "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
+	    "VLLM_CPU_SGL_KERNEL": 1,
+	    "VLLM_CPU_KVCACHE_SPACE": 40
+        },
+        "server_parameters": {
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
+            "pipeline_parallel_size": 3,
+	    "dtype": "bfloat16",
+	    "distributed_executor_backend": "mp",
+	    "block_size": 128,
+	    "trust_remote_code": "",
+	    "enable_chunked_prefill": "",
+            "disable_log_stats": "",
+	    "enforce_eager": "",
+	    "max_num_batched_tokens": 2048,
+	    "max_num_seqs": 256,
+            "load_format": "dummy"
+        },
+        "client_parameters": {
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
+            "backend": "vllm",
+            "dataset_name": "random",
+	    "random-input-len": 128,
+	    "random-output-len": 128,
+	    "ignore-eos": "",
+            "num_prompts": 1000
+        }
+    },
+    {
+        "test_name": "serving_llama8B_tp2pp3_random_128_128",
+        "qps_list": ["inf"],
+        "max_concurrency_list": [12, 16, 24, 32, 64, 128, 200, 1000],
+        "server_environment_variables": {
+            "VLLM_RPC_TIMEOUT": 100000,
+	    "VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
+	    "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
+	    "VLLM_CPU_SGL_KERNEL": 1,
+	    "VLLM_CPU_KVCACHE_SPACE": 40
+        },
+        "server_parameters": {
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
+            "tensor_parallel_size": 2,
+            "pipeline_parallel_size": 3,
+	    "dtype": "bfloat16",
+	    "distributed_executor_backend": "mp",
+	    "block_size": 128,
+	    "trust_remote_code": "",
+	    "enable_chunked_prefill": "",
+            "disable_log_stats": "",
+	    "enforce_eager": "",
+	    "max_num_batched_tokens": 2048,
+	    "max_num_seqs": 256,
+            "load_format": "dummy"
+        },
+        "client_parameters": {
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
+            "backend": "vllm",
+            "dataset_name": "random",
+	    "random-input-len": 128,
+	    "random-output-len": 128,
+	    "ignore-eos": "",
+            "num_prompts": 1000
+        }
+    }
+]
--- a/.buildkite/nightly-benchmarks/tests/serving-tests-cpu.json
+++ b/.buildkite/nightly-benchmarks/tests/serving-tests-cpu.json
@ -2,104 +2,112 @@
    {
        "test_name": "serving_llama8B_tp1_sharegpt",
        "qps_list": [1, 4, 16, "inf"],
+        "max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
        "server_environment_variables": {
            "VLLM_RPC_TIMEOUT": 100000,
 	    "VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
 	    "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
+	    "VLLM_CPU_SGL_KERNEL": 1,
 	    "VLLM_CPU_KVCACHE_SPACE": 40
        },
        "server_parameters": {
-            "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "tensor_parallel_size": 1,
 	    "dtype": "bfloat16",
 	    "distributed_executor_backend": "mp",
 	    "block_size": 128,
 	    "trust_remote_code": "",
            "disable_log_stats": "",
-            "disable_log_requests": "",
 	    "enforce_eager": "",
+	    "max_num_batched_tokens": 2048,
+	    "max_num_seqs": 256,
            "load_format": "dummy"
        },
        "client_parameters": {
-            "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "backend": "vllm",
            "dataset_name": "sharegpt",
            "dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
-	    "max_concurrency": 60,
            "num_prompts": 200
        }
    },
    {
        "test_name": "serving_llama8B_tp2_sharegpt",
        "qps_list": [1, 4, 16, "inf"],
+        "max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
        "server_environment_variables": {
            "VLLM_RPC_TIMEOUT": 100000,
 	    "VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
 	    "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
+	    "VLLM_CPU_SGL_KERNEL": 1,
 	    "VLLM_CPU_KVCACHE_SPACE": 40
        },
        "server_parameters": {
-            "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "tensor_parallel_size": 2,
 	    "dtype": "bfloat16",
 	    "distributed_executor_backend": "mp",
 	    "block_size": 128,
 	    "trust_remote_code": "",
            "disable_log_stats": "",
-            "disable_log_requests": "",
 	    "enforce_eager": "",
+	    "max_num_batched_tokens": 2048,
+	    "max_num_seqs": 256,
            "load_format": "dummy"
        },
        "client_parameters": {
-            "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "backend": "vllm",
            "dataset_name": "sharegpt",
            "dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
-	    "max_concurrency": 60,
            "num_prompts": 200
        }
    },
    {
        "test_name": "serving_llama8B_tp4_sharegpt",
        "qps_list": [1, 4, 16, "inf"],
+        "max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
        "server_environment_variables": {
            "VLLM_RPC_TIMEOUT": 100000,
 	    "VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
 	    "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
+	    "VLLM_CPU_SGL_KERNEL": 1,
 	    "VLLM_CPU_KVCACHE_SPACE": 40
        },
        "server_parameters": {
-            "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "tensor_parallel_size": 4,
 	    "dtype": "bfloat16",
 	    "distributed_executor_backend": "mp",
 	    "block_size": 128,
 	    "trust_remote_code": "",
            "disable_log_stats": "",
-            "disable_log_requests": "",
 	    "enforce_eager": "",
+	    "max_num_batched_tokens": 2048,
+	    "max_num_seqs": 256,
            "load_format": "dummy"
        },
        "client_parameters": {
-            "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "backend": "vllm",
            "dataset_name": "sharegpt",
            "dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
-	    "max_concurrency": 60,
            "num_prompts": 200
        }
    },
    {
        "test_name": "serving_llama8B_tp4_random_1024_128",
        "qps_list": [1, 4, 16, "inf"],
+        "max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
        "server_environment_variables": {
            "VLLM_RPC_TIMEOUT": 100000,
 	    "VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
 	    "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
+	    "VLLM_CPU_SGL_KERNEL": 1,
 	    "VLLM_CPU_KVCACHE_SPACE": 40
        },
        "server_parameters": {
-            "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "tensor_parallel_size": 4,
 	    "dtype": "bfloat16",
 	    "distributed_executor_backend": "mp",
@ -107,32 +115,34 @@
 	    "trust_remote_code": "",
 	    "enable_chunked_prefill": "",
            "disable_log_stats": "",
-            "disable_log_requests": "",
 	    "enforce_eager": "",
+	    "max_num_batched_tokens": 2048,
+	    "max_num_seqs": 256,
            "load_format": "dummy"
        },
        "client_parameters": {
-            "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "backend": "vllm",
            "dataset_name": "random",
 	    "random-input-len": 1024,
 	    "random-output-len": 128,
 	    "ignore-eos": "",
-	    "max_concurrency": 100,
            "num_prompts": 100
        }
    },
    {
        "test_name": "serving_llama8B_pp6_random_1024_128",
        "qps_list": [1, 4, 16, "inf"],
+        "max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
        "server_environment_variables": {
            "VLLM_RPC_TIMEOUT": 100000,
 	    "VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
 	    "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
+	    "VLLM_CPU_SGL_KERNEL": 1,
 	    "VLLM_CPU_KVCACHE_SPACE": 40
        },
        "server_parameters": {
-            "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "pipeline_parallel_size": 6,
 	    "dtype": "bfloat16",
 	    "distributed_executor_backend": "mp",
@ -140,18 +150,18 @@
 	    "trust_remote_code": "",
 	    "enable_chunked_prefill": "",
            "disable_log_stats": "",
-            "disable_log_requests": "",
 	    "enforce_eager": "",
+	    "max_num_batched_tokens": 2048,
+	    "max_num_seqs": 256,
            "load_format": "dummy"
        },
        "client_parameters": {
-            "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "backend": "vllm",
            "dataset_name": "random",
 	    "random-input-len": 1024,
 	    "random-output-len": 128,
 	    "ignore-eos": "",
-	    "max_concurrency": 100,
            "num_prompts": 100
        }
    }
--- a/.buildkite/nightly-benchmarks/tests/serving-tests.json
+++ b/.buildkite/nightly-benchmarks/tests/serving-tests.json
@ -7,7 +7,6 @@
            "tensor_parallel_size": 1,
            "swap_space": 16,
            "disable_log_stats": "",
-            "disable_log_requests": "",
            "load_format": "dummy"
        },
        "client_parameters": {
@ -26,7 +25,6 @@
            "tensor_parallel_size": 4,
            "swap_space": 16,
            "disable_log_stats": "",
-            "disable_log_requests": "",
            "load_format": "dummy"
        },
        "client_parameters": {
@ -45,7 +43,6 @@
            "tensor_parallel_size": 2,
            "swap_space": 16,
            "disable_log_stats": "",
-            "disable_log_requests": "",
            "load_format": "dummy"
        },
        "client_parameters": {
@ -60,8 +57,7 @@
        "test_name": "serving_llama70B_tp4_sharegpt_specdecode",
        "qps_list": [2],
        "server_parameters": {
-            "model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
-            "disable_log_requests": "", 
+            "model": "meta-llama/Meta-Llama-3.1-70B-Instruct", 
            "tensor_parallel_size": 4,
            "swap_space": 16,
            "speculative_config": {
--- a/.buildkite/nightly-benchmarks/tests/throughput-tests-cpu.json
+++ b/.buildkite/nightly-benchmarks/tests/throughput-tests-cpu.json
@ -6,7 +6,7 @@
 	    "VLLM_CPU_KVCACHE_SPACE": 40
        },
        "parameters": {
-            "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "tensor_parallel_size": 1,
            "load_format": "dummy",
            "dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json",
@ -21,7 +21,7 @@
 	    "VLLM_CPU_KVCACHE_SPACE": 40
        },
        "parameters": {
-            "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "tensor_parallel_size": 4,
            "load_format": "dummy",
            "dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json",
--- a/.buildkite/release-pipeline.yaml
+++ b/.buildkite/release-pipeline.yaml
@ -1,4 +1,20 @@
 steps:
+  # aarch64 + CUDA builds
+  - label: "Build arm64 wheel - CUDA 12.8"
+    id: build-wheel-arm64-cuda-12-8
+    agents:
+      queue: arm64_cpu_queue_postmerge
+    commands:
+      # #NOTE: torch_cuda_arch_list is derived from upstream PyTorch build files here:
+      # https://github.com/pytorch/pytorch/blob/main/.ci/aarch64_linux/aarch64_ci_build.sh#L7
+      - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.8.1 --build-arg torch_cuda_arch_list='8.7 9.0 10.0+PTX' --tag vllm-ci:build-image --target build --progress plain -f docker/Dockerfile ."
+      - "mkdir artifacts"
+      - "docker run --rm -v $(pwd)/artifacts:/artifacts_host vllm-ci:build-image bash -c 'cp -r dist /artifacts_host && chmod -R a+rw /artifacts_host'"
+      - "bash .buildkite/scripts/upload-wheels.sh"
+    env:
+      DOCKER_BUILDKIT: "1"
+
+  # x86 + CUDA builds
  - label: "Build wheel - CUDA 12.8"
    id: build-wheel-cuda-12-8
    agents:
@ -11,7 +27,12 @@ steps:
    env:
      DOCKER_BUILDKIT: "1"

+  - block: "Build CUDA 12.6 wheel"
+    key: block-build-cu126-wheel
+    depends_on: ~
+
  - label: "Build wheel - CUDA 12.6"
+    depends_on: block-build-cu126-wheel
    id: build-wheel-cuda-12-6
    agents:
      queue: cpu_queue_postmerge
@ -52,7 +73,7 @@ steps:
      queue: cpu_queue_postmerge
    commands:
      - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
-      - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.8.1 --build-arg INSTALL_KV_CONNECTORS=true --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT --target vllm-openai --progress plain -f docker/Dockerfile ."
+      - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.8.1 --build-arg FLASHINFER_AOT_COMPILE=true --build-arg INSTALL_KV_CONNECTORS=true --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT --target vllm-openai --progress plain -f docker/Dockerfile ."
      - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT"

  - label: "Annotate release workflow"
--- a/.buildkite/scripts/hardware_ci/run-amd-test.sh
+++ b/.buildkite/scripts/hardware_ci/run-amd-test.sh
@ -121,7 +121,6 @@ fi
 if [[ $commands == *" kernels/quantization"* ]]; then
  commands="${commands} \
  --ignore=kernels/quantization/test_int8_quant.py \
-  --ignore=kernels/quantization/test_aqlm.py \
  --ignore=kernels/quantization/test_machete_mm.py \
  --ignore=kernels/quantization/test_block_fp8.py \
  --ignore=kernels/quantization/test_block_int8.py \
--- a/.buildkite/scripts/hardware_ci/run-cpu-test.sh
+++ b/.buildkite/scripts/hardware_ci/run-cpu-test.sh
@ -13,9 +13,9 @@ NUMA_NODE=${NUMA_NODE:-1}
 export CMAKE_BUILD_PARALLEL_LEVEL=32

 # Setup cleanup
-remove_docker_container() { 
-    set -e; 
-    docker rm -f cpu-test-"$NUMA_NODE" cpu-test-"$NUMA_NODE"-avx2 || true; 
+remove_docker_container() {
+    set -e;
+    docker rm -f cpu-test-"$NUMA_NODE" cpu-test-"$NUMA_NODE"-avx2 || true;
 }
 trap remove_docker_container EXIT
 remove_docker_container
@ -46,6 +46,11 @@ function cpu_tests() {
    set -e
    python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m"

+  # Run kernel tests
+  docker exec cpu-test-"$NUMA_NODE" bash -c "
+    set -e
+    pytest -v -s tests/kernels/test_onednn.py"
+
  # Run basic model test
  docker exec cpu-test-"$NUMA_NODE" bash -c "
    set -e
@ -69,7 +74,7 @@ function cpu_tests() {
  docker exec cpu-test-"$NUMA_NODE" bash -c "
    set -e
    pytest -s -v \
-    tests/quantization/test_compressed_tensors.py::test_compressed_tensors_w8a8_logprobs[False-10-32-neuralmagic/Llama-3.2-1B-quantized.w8a8]" 
+    tests/quantization/test_compressed_tensors.py::test_compressed_tensors_w8a8_logprobs[False-10-32-neuralmagic/Llama-3.2-1B-quantized.w8a8]"

  # Note: disable it until supports V1
  # Run AWQ test
@ -78,25 +83,25 @@ function cpu_tests() {
  #   VLLM_USE_V1=0 pytest -s -v \
  #   tests/quantization/test_ipex_quant.py"

-  # online serving
-  docker exec cpu-test-"$NUMA_NODE" bash -c '
-    set -e
-    VLLM_CPU_OMP_THREADS_BIND=$E2E_OMP_THREADS VLLM_CPU_SGL_KERNEL=1 vllm serve meta-llama/Llama-3.2-3B-Instruct -tp=2 -pp=2 &
-    timeout 600 bash -c "until curl localhost:8000/v1/models; do sleep 1; done" || exit 1
-    python3 benchmarks/benchmark_serving.py \
-      --backend vllm \
-      --dataset-name random \
-      --model meta-llama/Llama-3.2-3B-Instruct \
-      --num-prompts 20 \
-      --endpoint /v1/completions'
-
  # Run multi-lora tests
  docker exec cpu-test-"$NUMA_NODE" bash -c "
    set -e
    pytest -s -v \
    tests/lora/test_qwen2vl.py"
+
+  # online serving
+  docker exec cpu-test-"$NUMA_NODE" bash -c '
+    set -e
+    VLLM_CPU_OMP_THREADS_BIND=$E2E_OMP_THREADS VLLM_CPU_SGL_KERNEL=1 vllm serve meta-llama/Llama-3.2-3B-Instruct -tp=2 -pp=2 &
+    timeout 600 bash -c "until curl localhost:8000/v1/models; do sleep 1; done" || exit 1
+    vllm bench serve \
+      --backend vllm \
+      --dataset-name random \
+      --model meta-llama/Llama-3.2-3B-Instruct \
+      --num-prompts 20 \
+      --endpoint /v1/completions'
 }

 # All of CPU tests are expected to be finished less than 40 mins.
 export -f cpu_tests
-timeout 1.5h bash -c "cpu_tests $CORE_RANGE $NUMA_NODE"
+timeout 2h bash -c "cpu_tests $CORE_RANGE $NUMA_NODE"
--- a/.buildkite/scripts/hardware_ci/run-gh200-test.sh
+++ b/.buildkite/scripts/hardware_ci/run-gh200-test.sh
@ -16,8 +16,7 @@ DOCKER_BUILDKIT=1 docker build . \
  --build-arg max_jobs=66 \
  --build-arg nvcc_threads=2 \
  --build-arg RUN_WHEEL_CHECK=false \
-  --build-arg torch_cuda_arch_list="9.0+PTX" \
-  --build-arg vllm_fa_cmake_gpu_arches="90-real"
+  --build-arg torch_cuda_arch_list="9.0+PTX"

 # Setup cleanup
 remove_docker_container() { docker rm -f gh200-test || true; }
--- a/.buildkite/scripts/hardware_ci/run-tpu-v1-test-part2.sh
+++ b/.buildkite/scripts/hardware_ci/run-tpu-v1-test-part2.sh
@ -0,0 +1,167 @@
+#!/bin/bash
+
+set -xu
+
+
+remove_docker_container() { 
+    docker rm -f tpu-test || true;
+}
+
+trap remove_docker_container EXIT
+
+# Remove the container that might not be cleaned up in the previous run.
+remove_docker_container
+
+# Build the docker image.
+docker build -f docker/Dockerfile.tpu -t vllm-tpu .
+
+# Set up cleanup.
+cleanup_docker() {
+  # Get Docker's root directory
+  docker_root=$(docker info -f '{{.DockerRootDir}}')
+  if [ -z "$docker_root" ]; then
+    echo "Failed to determine Docker root directory."
+    exit 1
+  fi
+  echo "Docker root directory: $docker_root"
+  # Check disk usage of the filesystem where Docker's root directory is located
+  disk_usage=$(df "$docker_root" | tail -1 | awk '{print $5}' | sed 's/%//')
+  # Define the threshold
+  threshold=70
+  if [ "$disk_usage" -gt "$threshold" ]; then
+    echo "Disk usage is above $threshold%. Cleaning up Docker images and volumes..."
+    # Remove dangling images (those that are not tagged and not used by any container)
+    docker image prune -f
+    # Remove unused volumes / force the system prune for old images as well.
+    docker volume prune -f && docker system prune --force --filter "until=72h" --all
+    echo "Docker images and volumes cleanup completed."
+  else
+    echo "Disk usage is below $threshold%. No cleanup needed."
+  fi
+}
+cleanup_docker
+
+# For HF_TOKEN.
+source /etc/environment
+
+docker run --privileged --net host --shm-size=16G -it \
+    -e "HF_TOKEN=$HF_TOKEN" --name tpu-test \
+    vllm-tpu /bin/bash -c '
+set -e # Exit immediately if a command exits with a non-zero status.
+set -u # Treat unset variables as an error.
+
+echo "--- Starting script inside Docker container ---"
+
+# Create results directory
+RESULTS_DIR=$(mktemp -d)
+# If mktemp fails, set -e will cause the script to exit.
+echo "Results will be stored in: $RESULTS_DIR"
+
+# Install dependencies
+echo "--- Installing Python dependencies ---"
+python3 -m pip install --progress-bar off git+https://github.com/thuml/depyf.git \
+    && python3 -m pip install --progress-bar off pytest pytest-asyncio tpu-info \
+    && python3 -m pip install --progress-bar off lm_eval[api]==0.4.4 \
+    && python3 -m pip install --progress-bar off hf-transfer
+echo "--- Python dependencies installed ---"
+export VLLM_USE_V1=1
+export VLLM_XLA_CHECK_RECOMPILATION=1
+export VLLM_XLA_CACHE_PATH=
+echo "Using VLLM V1"
+
+echo "--- Hardware Information ---"
+# tpu-info
+echo "--- Starting Tests ---"
+set +e
+overall_script_exit_code=0
+
+# --- Test Definitions ---
+# If a test fails, this function will print logs and will not cause the main script to exit.
+run_test() {
+    local test_num=$1
+    local test_name=$2
+    local test_command=$3
+    local log_file="$RESULTS_DIR/test_${test_num}.log"
+    local actual_exit_code
+
+    echo "--- TEST_$test_num: Running $test_name ---"
+    
+    # Execute the test command.
+    eval "$test_command" > >(tee -a "$log_file") 2> >(tee -a "$log_file" >&2)
+    actual_exit_code=$?
+
+    echo "TEST_${test_num}_COMMAND_EXIT_CODE: $actual_exit_code" # This goes to main log
+    echo "TEST_${test_num}_COMMAND_EXIT_CODE: $actual_exit_code" >> "$log_file" # Also to per-test log
+
+    if [ "$actual_exit_code" -ne 0 ]; then
+        echo "TEST_$test_num ($test_name) FAILED with exit code $actual_exit_code." >&2
+        echo "--- Log for failed TEST_$test_num ($test_name) ---" >&2
+        if [ -f "$log_file" ]; then
+            cat "$log_file" >&2
+        else
+            echo "Log file $log_file not found for TEST_$test_num ($test_name)." >&2
+        fi
+        echo "--- End of log for TEST_$test_num ($test_name) ---" >&2
+        return "$actual_exit_code" # Return the failure code
+    else
+        echo "TEST_$test_num ($test_name) PASSED."
+        return 0 # Return success
+    fi
+}
+
+# Helper function to call run_test and update the overall script exit code
+run_and_track_test() {
+    local test_num_arg="$1"
+    local test_name_arg="$2"
+    local test_command_arg="$3"
+
+    # Run the test
+    run_test "$test_num_arg" "$test_name_arg" "$test_command_arg"
+    local test_specific_exit_code=$?
+
+    # If the test failed, set the overall script exit code to 1
+    if [ "$test_specific_exit_code" -ne 0 ]; then
+        # No need for extra echo here, run_test already logged the failure.
+        overall_script_exit_code=1
+    fi
+}
+
+# --- Actual Test Execution ---
+run_and_track_test 1 "test_struct_output_generate.py" \
+    "python3 -m pytest -s -v /workspace/vllm/tests/v1/entrypoints/llm/test_struct_output_generate.py -k \"not test_structured_output_with_reasoning_matrices\""
+run_and_track_test 2 "test_moe_pallas.py" \
+    "python3 -m pytest -s -v /workspace/vllm/tests/tpu/test_moe_pallas.py"
+run_and_track_test 3 "test_lora.py" \
+    "VLLM_XLA_CHECK_RECOMPILATION=0 python3 -m pytest -s -v /workspace/vllm/tests/tpu/lora/test_lora.py"
+run_and_track_test 4 "test_tpu_qkv_linear.py" \
+    "python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_tpu_qkv_linear.py"
+run_and_track_test 5 "test_spmd_model_weight_loading.py" \
+    "python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_spmd_model_weight_loading.py"
+run_and_track_test 6 "test_kv_cache_update_kernel.py" \
+    "python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_kv_cache_update_kernel.py"
+run_and_track_test 7 "test_tpu_int8.py" \
+    "python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_tpu_int8.py"
+
+# After all tests have been attempted, exit with the overall status.
+if [ "$overall_script_exit_code" -ne 0 ]; then
+    echo "--- One or more tests FAILED. Overall script exiting with failure code 1. ---"
+else
+    echo "--- All tests have completed and PASSED. Overall script exiting with success code 0. ---"
+fi
+exit "$overall_script_exit_code"
+' # IMPORTANT: This is the closing single quote for the bash -c "..." command. Ensure it is present and correct.
+
+# Capture the exit code of the docker run command
+DOCKER_RUN_EXIT_CODE=$?
+
+# The trap will run for cleanup.
+# Exit the main script with the Docker run command's exit code.
+if [ "$DOCKER_RUN_EXIT_CODE" -ne 0 ]; then
+    echo "Docker run command failed with exit code $DOCKER_RUN_EXIT_CODE."
+    exit "$DOCKER_RUN_EXIT_CODE"
+else
+    echo "Docker run command completed successfully."
+    exit 0
+fi
+# TODO: This test fails because it uses RANDOM_SEED sampling
+# pytest -v -s /workspace/vllm/tests/tpu/test_custom_dispatcher.py \
--- a/.buildkite/scripts/hardware_ci/run-tpu-v1-test.sh
+++ b/.buildkite/scripts/hardware_ci/run-tpu-v1-test.sh
@ -5,7 +5,6 @@ set -xu

 remove_docker_container() { 
    docker rm -f tpu-test || true; 
-    docker rm -f vllm-tpu || true;
 }

 trap remove_docker_container EXIT
@ -150,18 +149,6 @@ run_and_track_test 9 "test_multimodal.py" \
    "python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_multimodal.py"
 run_and_track_test 10 "test_pallas.py" \
    "python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_pallas.py"
-run_and_track_test 11 "test_struct_output_generate.py" \
-    "HF_HUB_DISABLE_XET=1 python3 -m pytest -s -v /workspace/vllm/tests/v1/entrypoints/llm/test_struct_output_generate.py -k \"not test_structured_output_with_reasoning_matrices\""
-run_and_track_test 12 "test_moe_pallas.py" \
-    "python3 -m pytest -s -v /workspace/vllm/tests/tpu/test_moe_pallas.py"
-run_and_track_test 13 "test_lora.py" \
-    "VLLM_XLA_CHECK_RECOMPILATION=0 python3 -m pytest -s -v /workspace/vllm/tests/tpu/lora/test_lora.py"
-run_and_track_test 14 "test_tpu_qkv_linear.py" \
-    "python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_tpu_qkv_linear.py"
-run_and_track_test 15 "test_spmd_model_weight_loading.py" \
-    "python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_spmd_model_weight_loading.py"
-run_and_track_test 16 "test_kv_cache_update_kernel.py" \
-    "python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_kv_cache_update_kernel.py"

 # After all tests have been attempted, exit with the overall status.
 if [ "$overall_script_exit_code" -ne 0 ]; then
--- a/.buildkite/scripts/hardware_ci/run-xpu-test.sh
+++ b/.buildkite/scripts/hardware_ci/run-xpu-test.sh
@ -23,9 +23,13 @@ docker run \
    --device /dev/dri \
    -v /dev/dri/by-path:/dev/dri/by-path \
    --entrypoint="" \
+    -e "HF_TOKEN=${HF_TOKEN}" \
+    -e "ZE_AFFINITY_MASK=${ZE_AFFINITY_MASK}" \
    --name "${container_name}" \
    "${image_name}" \
-    sh -c '
+    bash -c '
+    set -e
+    echo $ZE_AFFINITY_MASK
    VLLM_USE_V1=1 python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager
    VLLM_USE_V1=1 python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend ray
    VLLM_USE_V1=1 python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend mp
@ -35,8 +39,8 @@ docker run \
    pytest -v -s v1/sample --ignore=v1/sample/test_logprobs.py --ignore=v1/sample/test_logprobs_e2e.py
    pytest -v -s v1/worker --ignore=v1/worker/test_gpu_model_runner.py
    pytest -v -s v1/structured_output
-    pytest -v -s v1/spec_decode --ignore=v1/spec_decode/test_max_len.py --ignore=v1/spec_decode/test_eagle.py
-    pytest -v -s v1/kv_connector/unit --ignore=v1/kv_connector/unit/test_multi_connector.py --ignore=v1/kv_connector/unit/test_nixl_connector.py
+    pytest -v -s v1/spec_decode --ignore=v1/spec_decode/test_max_len.py --ignore=v1/spec_decode/test_eagle.py --ignore=v1/spec_decode/test_tree_attention.py
+    pytest -v -s v1/kv_connector/unit --ignore=v1/kv_connector/unit/test_multi_connector.py --ignore=v1/kv_connector/unit/test_nixl_connector.py --ignore=v1/kv_connector/unit/test_shared_storage_connector.py
    pytest -v -s v1/test_serial_utils.py
    pytest -v -s v1/test_utils.py
    pytest -v -s v1/test_metrics_reader.py
--- a/.buildkite/scripts/run-benchmarks.sh
+++ b/.buildkite/scripts/run-benchmarks.sh
@ -11,10 +11,10 @@ cd "$(dirname "${BASH_SOURCE[0]}")/../.."
 (which wget && which curl) || (apt-get update && apt-get install -y wget curl)

 # run python-based benchmarks and upload the result to buildkite
-python3 benchmarks/benchmark_latency.py --output-json latency_results.json 2>&1 | tee benchmark_latency.txt
+vllm bench latency --output-json latency_results.json 2>&1 | tee benchmark_latency.txt
 bench_latency_exit_code=$?

-python3 benchmarks/benchmark_throughput.py --input-len 256 --output-len 256 --output-json throughput_results.json 2>&1 | tee benchmark_throughput.txt
+vllm bench throughput --input-len 256 --output-len 256 --output-json throughput_results.json 2>&1 | tee benchmark_throughput.txt
 bench_throughput_exit_code=$?

 # run server-based benchmarks and upload the result to buildkite
@ -24,7 +24,7 @@ wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/r

 # wait for server to start, timeout after 600 seconds
 timeout 600 bash -c 'until curl localhost:8000/v1/models; do sleep 1; done' || exit 1
-python3 benchmarks/benchmark_serving.py \
+vllm bench serve \
    --backend vllm \
    --dataset-name sharegpt \
    --dataset-path ./ShareGPT_V3_unfiltered_cleaned_split.json \
--- a/.buildkite/scripts/tpu/cleanup_docker.sh
+++ b/.buildkite/scripts/tpu/cleanup_docker.sh
@ -17,7 +17,7 @@ if [ "$disk_usage" -gt "$threshold" ]; then
  # Remove dangling images (those that are not tagged and not used by any container)
  docker image prune -f
  # Remove unused volumes / force the system prune for old images as well.
-  docker volume prune -f && docker system prune --force --filter "until=72h" --all
+  docker volume prune -f && docker system prune --force --filter "until=24h" --all
  echo "Docker images and volumes cleanup completed."
 else
  echo "Disk usage is below $threshold%. No cleanup needed."
--- a/.buildkite/scripts/tpu/config_v6e_1.env
+++ b/.buildkite/scripts/tpu/config_v6e_1.env
@ -1,6 +1,6 @@
 # Environment config
 TEST_NAME=llama8b
-CONTAINER_NAME=vllm-tpu
+CONTAINER_NAME=tpu-test

 # vllm config
 MODEL=meta-llama/Llama-3.1-8B-Instruct
--- a/.buildkite/scripts/tpu/docker_run_bm.sh
+++ b/.buildkite/scripts/tpu/docker_run_bm.sh
@ -12,8 +12,6 @@ source /etc/environment
 source $ENV_FILE

 remove_docker_container() { 
-    docker rm -f tpu-test || true; 
-    docker rm -f vllm-tpu || true;
    docker rm -f $CONTAINER_NAME || true;
 }

--- a/.buildkite/scripts/tpu/quantized_v6e_1.env
+++ b/.buildkite/scripts/tpu/quantized_v6e_1.env
@ -1,6 +1,6 @@
 # Environment config
 TEST_NAME=llama8bw8a8
-CONTAINER_NAME=vllm-tpu
+CONTAINER_NAME=tpu-test

 # vllm config
 MODEL=RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a8
--- a/.buildkite/scripts/tpu/run_bm.sh
+++ b/.buildkite/scripts/tpu/run_bm.sh
@ -44,7 +44,6 @@ echo

 VLLM_USE_V1=1 vllm serve $MODEL \
 --seed 42 \
- --disable-log-requests \
 --max-num-seqs $MAX_NUM_SEQS \
 --max-num-batched-tokens $MAX_NUM_BATCHED_TOKENS \
 --tensor-parallel-size $TENSOR_PARALLEL_SIZE \
@ -77,7 +76,7 @@ done
 echo "run benchmark test..."
 echo "logging to $BM_LOG"
 echo
-python benchmarks/benchmark_serving.py \
+vllm bench serve \
    --backend vllm \
    --model $MODEL  \
    --dataset-name sonnet \
--- a/.buildkite/scripts/upload-wheels.sh
+++ b/.buildkite/scripts/upload-wheels.sh
@ -14,8 +14,19 @@ fi
 # Get the single wheel file
 wheel="${wheel_files[0]}"

-# Rename 'linux' to 'manylinux1' in the wheel filename
-new_wheel="${wheel/linux/manylinux1}"
+# Detect architecture and rename 'linux' to appropriate manylinux version
+arch=$(uname -m)
+if [[ $arch == "x86_64" ]]; then
+    manylinux_version="manylinux1"
+elif [[ $arch == "aarch64" ]]; then
+    manylinux_version="manylinux2014"
+else
+    echo "Warning: Unknown architecture $arch, using manylinux1 as default"
+    manylinux_version="manylinux1"
+fi
+
+# Rename 'linux' to the appropriate manylinux version in the wheel filename
+new_wheel="${wheel/linux/$manylinux_version}"
 mv -- "$wheel" "$new_wheel"
 wheel="$new_wheel"

--- a/.buildkite/test-pipeline.yaml
+++ b/.buildkite/test-pipeline.yaml
@ -31,16 +31,6 @@
 steps:
 ##### fast check tests  #####

- label: Documentation Build # 2min
-  mirror_hardwares: [amdexperimental]
-  working_dir: "/vllm-workspace/test_docs"
-  fast_check: true
-  no_gpu: True
-  commands:
-  - pip install -r ../requirements/docs.txt
-  # TODO: add `--strict` once warnings in docstrings are fixed
-  - mkdocs build
-
 - label: Pytorch Nightly Dependency Override Check # 2min
  # if this test fails, it means the nightly torch version is not compatible with some
  # of the dependencies. Please check the error message and add the package to whitelist
@ -57,20 +47,20 @@ steps:
  - vllm/
  - tests/mq_llm_engine
  - tests/async_engine
-  - tests/test_inputs
+  - tests/test_inputs.py
+  - tests/test_outputs.py
  - tests/multimodal
-  - tests/test_utils
+  - tests/utils_
  - tests/worker
  - tests/standalone_tests/lazy_imports.py
  commands:
  - python3 standalone_tests/lazy_imports.py
  - pytest -v -s mq_llm_engine # MQLLMEngine
  - pytest -v -s async_engine # AsyncLLMEngine
-  - NUM_SCHEDULER_STEPS=4 pytest -v -s async_engine/test_async_llm_engine.py
  - pytest -v -s test_inputs.py
  - pytest -v -s test_outputs.py
  - pytest -v -s multimodal
-  - pytest -v -s test_utils.py # Utils
+  - pytest -v -s utils_ # Utils
  - pytest -v -s worker # Worker

 - label: Python-only Installation Test
@ -82,7 +72,7 @@ steps:
  - bash standalone_tests/python_only_compile.sh

 - label: Basic Correctness Test # 30min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
  fast_check: true
  torch_nightly: true
  source_file_dependencies:
@ -98,17 +88,8 @@ steps:
  - pytest -v -s basic_correctness/test_cpu_offload.py
  - VLLM_TEST_ENABLE_ARTIFICIAL_PREEMPT=1 pytest -v -s basic_correctness/test_preemption.py

- label: Chunked Prefill Test
-  mirror_hardwares: [amdexperimental, amdproduction]
-  source_file_dependencies:
-  - vllm/
-  - tests/basic_correctness/test_chunked_prefill
-  commands:
-  - VLLM_ATTENTION_BACKEND=XFORMERS pytest -v -s basic_correctness/test_chunked_prefill.py
-  - VLLM_ATTENTION_BACKEND=FLASH_ATTN pytest -v -s basic_correctness/test_chunked_prefill.py
-
 - label: Core Test # 10min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
  fast_check: true
  source_file_dependencies:
  - vllm/core
@ -128,11 +109,10 @@ steps:
  - tests/entrypoints/offline_mode
  commands:
  - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-  - pytest -v -s entrypoints/llm --ignore=entrypoints/llm/test_lazy_outlines.py --ignore=entrypoints/llm/test_generate.py --ignore=entrypoints/llm/test_generate_multiple_loras.py --ignore=entrypoints/llm/test_guided_generate.py --ignore=entrypoints/llm/test_collective_rpc.py
+  - pytest -v -s entrypoints/llm --ignore=entrypoints/llm/test_lazy_outlines.py --ignore=entrypoints/llm/test_generate.py --ignore=entrypoints/llm/test_generate_multiple_loras.py --ignore=entrypoints/llm/test_collective_rpc.py
  - pytest -v -s entrypoints/llm/test_lazy_outlines.py # it needs a clean process
  - pytest -v -s entrypoints/llm/test_generate.py # it needs a clean process
  - pytest -v -s entrypoints/llm/test_generate_multiple_loras.py # it needs a clean process
-  - VLLM_USE_V1=0 pytest -v -s entrypoints/llm/test_guided_generate.py # it needs a clean process
  - VLLM_USE_V1=0 pytest -v -s entrypoints/offline_mode # Needs to avoid interference with other tests

 - label: Entrypoints Test (API Server) # 40min
@ -146,7 +126,8 @@ steps:
  - tests/entrypoints/test_chat_utils
  commands:
  - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-  - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/test_oot_registration.py --ignore=entrypoints/openai/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/
+  - PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/openai/test_collective_rpc.py # PYTHONPATH is needed to import custom Worker extension
+  - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/test_oot_registration.py --ignore=entrypoints/openai/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/test_collective_rpc.py
  - pytest -v -s entrypoints/test_chat_utils.py

 - label: Distributed Tests (4 GPUs) # 10min
@ -210,7 +191,7 @@ steps:
  - pytest -v -s distributed/test_eplb_execute.py

 - label: Metrics, Tracing Test # 10min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
  num_gpus: 2
  source_file_dependencies:
  - vllm/
@ -229,7 +210,7 @@ steps:
 #####  1 GPU test  #####

 - label: Regression Test # 5min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
  source_file_dependencies:
  - vllm/
  - tests/test_regression
@ -264,6 +245,7 @@ steps:
    - pytest -v -s v1/engine
    - pytest -v -s v1/entrypoints
    - pytest -v -s v1/sample
+    - pytest -v -s v1/logits_processors
    - pytest -v -s v1/worker
    - pytest -v -s v1/structured_output
    - pytest -v -s v1/spec_decode
@ -281,7 +263,7 @@ steps:
    - pytest -v -s entrypoints/openai/correctness/test_lmeval.py::test_lm_eval_accuracy_v1_engine

 - label: Examples Test # 25min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
  working_dir: "/vllm-workspace/examples"
  source_file_dependencies:
  - vllm/entrypoints
@ -305,17 +287,8 @@ steps:
    - python3 offline_inference/basic/score.py
    - VLLM_USE_V1=0 python3 offline_inference/profiling.py --model facebook/opt-125m run_num_steps --num-steps 2

- label: Prefix Caching Test # 9min
-  mirror_hardwares: [amdexperimental, amdproduction]
-  source_file_dependencies:
-  - vllm/
-  - tests/prefix_caching
-  commands:
-    - pytest -v -s prefix_caching
-
-
 - label: Platform Tests (CUDA)
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
  source_file_dependencies:
  - vllm/
  - tests/cuda
@ -331,7 +304,6 @@ steps:
  - tests/conftest.py
  commands:
    - pytest -v -s samplers
-    - VLLM_USE_FLASHINFER_SAMPLER=1 pytest -v -s samplers

 - label: LoRA Test %N # 15min each
  mirror_hardwares: [amdexperimental]
@ -354,9 +326,11 @@ steps:
    - pytest -v -s compile/test_silu_mul_quant_fusion.py
    - pytest -v -s compile/test_sequence_parallelism.py
    - pytest -v -s compile/test_async_tp.py
+    - pytest -v -s compile/test_fusion_all_reduce.py
+    - pytest -v -s compile/test_decorator.py

 - label: PyTorch Fullgraph Smoke Test # 9min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
  torch_nightly: true
  source_file_dependencies:
  - vllm/
@ -367,9 +341,10 @@ steps:
  - pytest -v -s compile/piecewise/test_simple.py
  - pytest -v -s compile/piecewise/test_toy_llama.py
  - pytest -v -s compile/piecewise/test_full_cudagraph.py
+  - pytest -v -s compile/piecewise/test_multiple_graphs.py

 - label: PyTorch Fullgraph Test # 18min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
  torch_nightly: true
  source_file_dependencies:
  - vllm/
@ -378,7 +353,7 @@ steps:
  - pytest -v -s compile/test_full_graph.py

 - label: Kernels Core Operation Test
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
  source_file_dependencies:
  - csrc/
  - tests/kernels/core
@ -403,20 +378,22 @@ steps:
  - vllm/model_executor/layers/quantization
  - tests/kernels/quantization
  commands:
-    - pytest -v -s kernels/quantization  --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
+    - pytest -v -s kernels/quantization --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
  parallelism: 2

- label: Kernels MoE Test
+- label: Kernels MoE Test %N
  mirror_hardwares: [amdexperimental]
  source_file_dependencies:
+  - csrc/quantization/cutlass_w8a8/moe/
  - csrc/moe/
  - tests/kernels/moe
  - vllm/model_executor/layers/fused_moe/
  commands:
-    - pytest -v -s kernels/moe
+    - pytest -v -s kernels/moe --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
+  parallelism: 2

 - label: Kernels Mamba Test
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
  source_file_dependencies:
  - csrc/mamba/
  - tests/kernels/mamba
@ -424,8 +401,7 @@ steps:
    - pytest -v -s kernels/mamba

 - label: Tensorizer Test # 11min
-  mirror_hardwares: [amdexperimental, amdproduction]
-  soft_fail: true
+  mirror_hardwares: [amdexperimental]
  source_file_dependencies:
  - vllm/model_executor/model_loader
  - tests/tensorizer_loader
@ -437,7 +413,7 @@ steps:
    - pytest -v -s entrypoints/openai/test_tensorizer_entrypoint.py

 - label: Model Executor Test
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
  source_file_dependencies:
  - vllm/model_executor
  - tests/model_executor
@ -447,7 +423,7 @@ steps:
    - pytest -v -s model_executor

 - label: Benchmarks # 9min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
  working_dir: "/vllm-workspace/.buildkite"
  source_file_dependencies:
  - benchmarks/
@ -455,7 +431,7 @@ steps:
  - bash scripts/run-benchmarks.sh

 - label: Benchmarks CLI Test # 10min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
  source_file_dependencies:
  - vllm/
  - tests/benchmarks/
@ -476,13 +452,11 @@ steps:

 - label: LM Eval Small Models # 53min
  mirror_hardwares: [amdexperimental]
-  working_dir: "/vllm-workspace/.buildkite/lm-eval-harness"
  source_file_dependencies:
  - csrc/
  - vllm/model_executor/layers/quantization
  commands:
-  - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-  - pytest -s -v test_lm_eval_correctness.py --config-list-file=configs/models-small.txt --tp-size=1
+  - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt --tp-size=1

 - label: OpenAI API correctness
  mirror_hardwares: [amdexperimental]
@ -494,7 +468,7 @@ steps:
  - pytest -s entrypoints/openai/correctness/

 - label: Encoder Decoder tests # 5min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
  source_file_dependencies:
  - vllm/
  - tests/encoder_decoder
@ -502,7 +476,7 @@ steps:
    - pytest -v -s encoder_decoder

 - label: OpenAI-Compatible Tool Use # 20 min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
  fast_check: false
  source_file_dependencies:
    - vllm/
@ -534,8 +508,6 @@ steps:
  - vllm/
  - tests/models/language
  commands:
-    # Install causal-conv1d for plamo2 models here, as it is not compatible with pip-compile.
-    - pip install 'git+https://github.com/Dao-AILab/causal-conv1d@v1.5.0.post8'
    - pip freeze | grep -E 'torch'
    - pytest -v -s models/language -m core_model

@ -546,8 +518,10 @@ steps:
  - vllm/
  - tests/models/language/generation
  commands:
-    # Install causal-conv1d for plamo2 models here, as it is not compatible with pip-compile.
-    - pip install 'git+https://github.com/Dao-AILab/causal-conv1d@v1.5.0.post8'
+    # Install fast path packages for testing against transformers
+    # Note: also needed to run plamo2 model in vLLM
+    - uv pip install --system --no-build-isolation 'git+https://github.com/state-spaces/mamba@v2.2.5'
+    - uv pip install --system --no-build-isolation 'git+https://github.com/Dao-AILab/causal-conv1d@v1.5.2'
    - pytest -v -s models/language/generation -m hybrid_model

 - label: Language Models Test (Extended Generation) # 1hr20min
@ -570,6 +544,15 @@ steps:
  commands:
    - pytest -v -s models/language/pooling -m 'not core_model'

+- label: Multi-Modal Processor Test
+  source_file_dependencies:
+  - vllm/
+  - tests/models/multimodal
+  commands:
+    - pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
+    - pytest -v -s models/multimodal/processing --ignore models/multimodal/processing/test_tensor_schema.py
+    - pytest -v -s models/multimodal/processing/test_tensor_schema.py
+
 - label: Multi-Modal Models Test (Standard)
  mirror_hardwares: [amdexperimental]
  torch_nightly: true
@ -579,8 +562,7 @@ steps:
  commands:
    - pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
    - pip freeze | grep -E 'torch'
-    - pytest -v -s models/multimodal/processing
-    - pytest -v -s --ignore models/multimodal/generation/test_whisper.py models/multimodal -m core_model
+    - pytest -v -s models/multimodal -m core_model --ignore models/multimodal/generation/test_whisper.py --ignore models/multimodal/processing
    - cd .. && pytest -v -s tests/models/multimodal/generation/test_whisper.py -m core_model  # Otherwise, mp_method="spawn" doesn't work

 - label: Multi-Modal Models Test (Extended) 1
@ -591,7 +573,7 @@ steps:
  - tests/models/multimodal
  commands:
    - pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
-    - pytest -v -s --ignore models/multimodal/generation/test_common.py --ignore models/multimodal/processing models/multimodal -m 'not core_model'
+    - pytest -v -s models/multimodal -m 'not core_model' --ignore models/multimodal/generation/test_common.py --ignore models/multimodal/processing

 - label: Multi-Modal Models Test (Extended) 2
  mirror_hardwares: [amdexperimental]
@ -623,7 +605,7 @@ steps:

 # This test is used only in PR development phase to test individual models and should never run on main
 - label: Custom Models Test
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
  optional: true
  commands:
    - echo 'Testing custom models...'
@ -643,11 +625,46 @@ steps:
    - python3 examples/offline_inference/audio_language.py --model-type whisper
    - python3 examples/offline_inference/vision_language.py --model-type qwen2_5_vl

+- label: Blackwell Test
+  working_dir: "/vllm-workspace/"
+  gpu: b200
+  # optional: true
+  source_file_dependencies:
+  - csrc/quantization/fp4/
+  - csrc/attention/mla/
+  - csrc/quantization/cutlass_w8a8/moe/
+  - vllm/model_executor/layers/fused_moe/cutlass_moe.py
+  - vllm/model_executor/layers/fused_moe/flashinfer_cutlass_moe.py
+  - vllm/model_executor/layers/fused_moe/flashinfer_cutlass_prepare_finalize.py
+  - vllm/model_executor/layers/quantization/utils/flashinfer_utils.py
+  - vllm/v1/attention/backends/flashinfer.py
+  - vllm/compilation/fusion.py
+  - vllm/compilation/fusion_attn.py
+  commands:
+    - nvidia-smi
+    - python3 examples/offline_inference/basic/chat.py
+    # Attention
+    # num_heads2 broken by https://github.com/flashinfer-ai/flashinfer/issues/1353
+    - pytest -v -s tests/kernels/attention/test_flashinfer.py -k 'not num_heads2'
+    - pytest -v -s tests/kernels/attention/test_flashinfer_trtllm_attention.py
+    - pytest -v -s tests/kernels/test_cutlass_mla_decode.py
+    # Quantization
+    - pytest -v -s tests/kernels/quantization/test_cutlass_scaled_mm.py -k 'fp8'
+    - pytest -v -s tests/kernels/quantization/test_nvfp4_quant.py
+    - pytest -v -s tests/kernels/quantization/test_nvfp4_scaled_mm.py
+    - pytest -v -s tests/kernels/quantization/test_flashinfer_nvfp4_scaled_mm.py
+    - pytest -v -s tests/kernels/moe/test_nvfp4_moe.py
+    - pytest -v -s tests/kernels/moe/test_mxfp4_moe.py
+    # Fusion
+    - pytest -v -s tests/compile/test_fusion_all_reduce.py
+    - pytest -v -s tests/compile/test_fusion_attn.py::test_attention_quant_pattern
+    - pytest -v -s tests/kernels/moe/test_flashinfer.py
+
 #####  1 GPU test  #####
 #####  multi gpus test  #####

 - label: Distributed Comm Ops Test # 7min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
  working_dir: "/vllm-workspace/tests"
  num_gpus: 2
  source_file_dependencies:
@ -718,7 +735,6 @@ steps:
  # this test fails consistently.
  # TODO: investigate and fix
  - VLLM_USE_V1=0 CUDA_VISIBLE_DEVICES=0,1 pytest -v -s test_sharded_state_loader.py
-  - VLLM_USE_V1=0 CUDA_VISIBLE_DEVICES=0,1 pytest -v -s kv_transfer/test_disagg.py
  - CUDA_VISIBLE_DEVICES=0,1 pytest -v -s v1/shutdown
  - pytest -v -s models/multimodal/generation/test_maverick.py

@ -743,29 +759,8 @@ steps:
  - pytest -v -s models/test_oot_registration.py # it needs a clean process
  - pytest -v -s plugins/lora_resolvers # unit tests for in-tree lora resolver plugins

- label: Multi-step Tests (4 GPUs) # 36min
-  mirror_hardwares: [amdexperimental, amdproduction]
-  working_dir: "/vllm-workspace/tests"
-  num_gpus: 4
-  source_file_dependencies:
-  - vllm/model_executor/layers/sampler.py
-  - vllm/sequence.py
-  - vllm/worker/worker_base.py
-  - vllm/worker/worker.py
-  - vllm/worker/multi_step_worker.py
-  - vllm/worker/model_runner_base.py
-  - vllm/worker/model_runner.py
-  - vllm/worker/multi_step_model_runner.py
-  - vllm/engine
-  - tests/multi_step
-  commands:
-  # this test is quite flaky
-  # TODO: investigate and fix.
-  # - pytest -v -s multi_step/test_correctness_async_llm.py
-  - pytest -v -s multi_step/test_correctness_llm.py
-
 - label: Pipeline Parallelism Test # 45min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
  working_dir: "/vllm-workspace/tests"
  num_gpus: 4
  source_file_dependencies:
@ -779,7 +774,7 @@ steps:
  - pytest -v -s distributed/test_pipeline_parallel.py

 - label: LoRA TP Test (Distributed)
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
  num_gpus: 4
  source_file_dependencies:
  - vllm/lora
@ -792,6 +787,7 @@ steps:
    # requires multi-GPU testing for validation.
    - pytest -v -s -x lora/test_chatglm3_tp.py
    - pytest -v -s -x lora/test_llama_tp.py
+    - pytest -v -s -x lora/test_multi_loras_with_tp.py


 - label: Weight Loading Multiple GPU Test  # 33min
--- a/.github/CODEOWNERS
+++ b/.github/CODEOWNERS
@ -9,8 +9,8 @@
 /vllm/worker/worker_base.py @zhuohan123 @youkaichao @alexm-redhat @comaniac @njhill
 /vllm/worker/worker.py @zhuohan123 @youkaichao @alexm-redhat @comaniac @njhill
 /vllm/model_executor/layers/sampler.py @zhuohan123 @youkaichao @alexm-redhat @comaniac @njhill
-/vllm/model_executor/layers/quantization @mgoin @robertgshaw2-redhat @tlrmchlsmth
-/vllm/model_executor/guided_decoding @mgoin @russellb @aarnphm
+/vllm/model_executor/layers/quantization @mgoin @robertgshaw2-redhat @tlrmchlsmth @yewentao256
+/vllm/model_executor/layers/mamba @tdoublep
 /vllm/multimodal @DarkLight1337 @ywang96
 /vllm/vllm_flash_attn @LucasWilkinson
 /vllm/lora @jeejeelee
@ -21,34 +21,62 @@ CMakeLists.txt @tlrmchlsmth @LucasWilkinson

 # Any change to the VllmConfig changes can have a large user-facing impact,
 # so spam a lot of people
-/vllm/config.py @simon-mo @WoosukKwon @youkaichao @robertgshaw2-redhat @mgoin @tlrmchlsmth @houseroad @hmellor
+/vllm/config @simon-mo @WoosukKwon @youkaichao @robertgshaw2-redhat @mgoin @tlrmchlsmth @houseroad @hmellor @yewentao256 @ProExpertProg

 # vLLM V1
 /vllm/v1 @WoosukKwon @robertgshaw2-redhat @njhill @ywang96 @comaniac @alexm-redhat
 /vllm/v1/structured_output @mgoin @russellb @aarnphm
+/vllm/v1/attention/backends/triton_attn.py @tdoublep

 # Test ownership
 /.buildkite/lm-eval-harness @mgoin @simon-mo
 /tests/async_engine @njhill @robertgshaw2-redhat @simon-mo
-/tests/basic_correctness/test_chunked_prefill @rkooo567 @comaniac
 /tests/distributed/test_multi_node_assignment.py @youkaichao
 /tests/distributed/test_pipeline_parallel.py @youkaichao
 /tests/distributed/test_same_node.py @youkaichao
 /tests/entrypoints @DarkLight1337 @robertgshaw2-redhat @simon-mo @aarnphm
-/tests/entrypoints/llm/test_guided_generate.py @mgoin @russellb @aarnphm
-/tests/kernels @tlrmchlsmth @WoosukKwon
-/tests/model_executor/test_guided_processors.py @mgoin @russellb
+/tests/kernels @tlrmchlsmth @WoosukKwon @yewentao256
 /tests/models @DarkLight1337 @ywang96
-/tests/multi_step @alexm-redhat @comaniac
 /tests/multimodal @DarkLight1337 @ywang96
 /tests/prefix_caching @comaniac @KuntaiDu
-/tests/quantization @mgoin @robertgshaw2-redhat
+/tests/quantization @mgoin @robertgshaw2-redhat @yewentao256
 /tests/test_inputs.py @DarkLight1337 @ywang96
 /tests/v1/entrypoints/llm/test_struct_output_generate.py @mgoin @russellb @aarnphm
 /tests/v1/structured_output @mgoin @russellb @aarnphm
-/tests/weight_loading @mgoin @youkaichao
+/tests/weight_loading @mgoin @youkaichao @yewentao256
 /tests/lora @jeejeelee
+/tests/models/language/generation/test_hybrid.py @tdoublep

 # Docs
 /docs @hmellor
 mkdocs.yaml @hmellor
+
+# CPU
+/vllm/v1/worker/^cpu @bigPYJ1151
+/csrc/cpu @bigPYJ1151
+/vllm/platforms/cpu.py @bigPYJ1151
+/cmake/cpu_extension.cmake @bigPYJ1151
+/docker/Dockerfile.cpu @bigPYJ1151
+
+# Intel GPU
+/vllm/v1/worker/^xpu @jikunshang
+/vllm/platforms/xpu.py @jikunshang
+/docker/Dockerfile.xpu @jikunshang
+
+# Qwen-specific files
+/vllm/attention/backends/dual_chunk_flash_attn.py @sighingnow
+/vllm/model_executor/models/qwen* @sighingnow
+
+# Mistral-specific files
+/vllm/model_executor/models/mistral*.py @patrickvonplaten
+/vllm/model_executor/models/mixtral*.py @patrickvonplaten
+/vllm/model_executor/models/voxtral*.py @patrickvonplaten
+/vllm/model_executor/models/pixtral*.py @patrickvonplaten
+/vllm/transformers_utils/configs/mistral.py @patrickvonplaten
+/vllm/transformers_utils/tokenizers/mistral.py @patrickvonplaten
+
+# Kernels
+/vllm/attention/ops/chunked_prefill_paged_decode.py @tdoublep
+/vllm/attention/ops/triton_unified_attention.py @tdoublep
+
+
--- a/.github/PULL_REQUEST_TEMPLATE.md
+++ b/.github/PULL_REQUEST_TEMPLATE.md
@ -1,10 +1,5 @@
-## Essential Elements of an Effective PR Description Checklist
- [ ] The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
- [ ] The test plan, such as providing test command.
- [ ] The test results, such as pasting the results comparison before and after, or e2e results
- [ ] (Optional) The necessary documentation update, such as updating `supported_models.md` and `examples` for a new model.
-
-PLEASE FILL IN THE PR DESCRIPTION HERE ENSURING ALL CHECKLIST ITEMS ABOVE HAVE BEEN CONSIDERED.
+<!-- markdownlint-disable -->
+PLEASE FILL IN THE PR DESCRIPTION HERE ENSURING ALL CHECKLIST ITEMS (AT THE BOTTOM) HAVE BEEN CONSIDERED.

 ## Purpose

@ -14,5 +9,14 @@ PLEASE FILL IN THE PR DESCRIPTION HERE ENSURING ALL CHECKLIST ITEMS ABOVE HAVE B

 ## (Optional) Documentation Update

-<!--- pyml disable-next-line no-emphasis-as-heading -->
+---
+<details>
+<summary> Essential Elements of an Effective PR Description Checklist </summary>
+
+- [ ] The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
+- [ ] The test plan, such as providing test command.
+- [ ] The test results, such as pasting the results comparison before and after, or e2e results
+- [ ] (Optional) The necessary documentation update, such as updating `supported_models.md` and `examples` for a new model.
+</details>
+
 **BEFORE SUBMITTING, PLEASE READ <https://docs.vllm.ai/en/latest/contributing>** (anything written below this line will be removed by GitHub Actions)
--- a/.github/mergify.yml
+++ b/.github/mergify.yml
@ -118,6 +118,20 @@ pull_request_rules:
      add:
        - qwen

+- name: label-gpt-oss
+  description: Automatically apply gpt-oss label
+  conditions:
+    - or:
+      - files~=^examples/.*gpt[-_]?oss.*\.py
+      - files~=^tests/.*gpt[-_]?oss.*\.py
+      - files~=^vllm/model_executor/models/.*gpt[-_]?oss.*\.py
+      - files~=^vllm/model_executor/layers/.*gpt[-_]?oss.*\.py
+      - title~=(?i)gpt[-_]?oss
+  actions:
+    label:
+      add:
+        - gpt-oss
+
 - name: label-rocm
  description: Automatically apply rocm label
  conditions:
@ -149,9 +163,6 @@ pull_request_rules:
      - files=examples/offline_inference/structured_outputs.py
      - files=examples/online_serving/openai_chat_completion_structured_outputs.py
      - files=examples/online_serving/openai_chat_completion_structured_outputs_with_reasoning.py
-      - files~=^vllm/model_executor/guided_decoding/
-      - files=tests/model_executor/test_guided_processors.py
-      - files=tests/entrypoints/llm/test_guided_generate.py
      - files~=^tests/v1/structured_output/
      - files=tests/v1/entrypoints/llm/test_guided_generate.py
      - files~=^vllm/v1/structured_output/
--- a/.github/scripts/cleanup_pr_body.sh
+++ b/.github/scripts/cleanup_pr_body.sh
@ -15,11 +15,11 @@ NEW=/tmp/new_pr_body.txt
 gh pr view --json body --template "{{.body}}" "${PR_NUMBER}" > "${OLD}"
 cp "${OLD}" "${NEW}"

-# Remove "FIX #xxxx (*link existing issues this PR will resolve*)"
-sed -i '/FIX #xxxx.*$/d' "${NEW}"
+# Remove markdown comments (like the <!-- markdownlint-disable --> at the start)
+sed -i '/<!--.*-->$/d' "${NEW}"

-# Remove "FILL IN THE PR DESCRIPTION HERE"
-sed -i '/FILL IN THE PR DESCRIPTION HERE/d' "${NEW}"
+# Remove "PLEASE FILL IN THE PR DESCRIPTION HERE ENSURING ALL CHECKLIST ITEMS (AT THE BOTTOM) HAVE BEEN CONSIDERED."
+sed -i '/PLEASE FILL IN THE PR DESCRIPTION HERE.*$/d' "${NEW}"

 # Remove all lines after and including "**BEFORE SUBMITTING, PLEASE READ THE CHECKLIST BELOW AND FILL IN THE DESCRIPTION ABOVE**"
 sed -i '/\*\*BEFORE SUBMITTING, PLEASE READ.*\*\*/,$d' "${NEW}"
--- a/.github/workflows/lint-and-deploy.yaml
+++ b/.github/workflows/lint-and-deploy.yaml
@ -2,6 +2,10 @@ name: Lint and Deploy Charts

 on: pull_request

+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
 permissions:
  contents: read

--- a/.github/workflows/matchers/markdownlint.json
+++ b/.github/workflows/matchers/markdownlint.json
@ -0,0 +1,17 @@
+{
+  "problemMatcher": [
+    {
+      "owner": "markdownlint",
+      "pattern": [
+        {
+          "regexp": "^([^:]*):(\\d+):?(\\d+)?\\s([\\w-\\/]*)\\s(.*)$",
+          "file": 1,
+          "line": 2,
+          "column": 3,
+          "code": 4,
+          "message": 5
+        }
+      ]
+    }
+  ]
+}
--- a/.github/workflows/pre-commit.yml
+++ b/.github/workflows/pre-commit.yml
@ -5,6 +5,10 @@ on:
  push:
    branches: [main]

+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
+
 permissions:
  contents: read

@ -17,6 +21,7 @@ jobs:
      with:
        python-version: "3.12"
    - run: echo "::add-matcher::.github/workflows/matchers/actionlint.json"
+    - run: echo "::add-matcher::.github/workflows/matchers/markdownlint.json"
    - run: echo "::add-matcher::.github/workflows/matchers/mypy.json"
    - uses: pre-commit/action@2c7b3805fd2a0fd8c1884dcaebf91fc102a13ecd # v3.0.1
      with:
--- a/.github/workflows/scripts/build.sh
+++ b/.github/workflows/scripts/build.sh
@ -15,7 +15,6 @@ $python_executable -m pip install -r requirements/build.txt -r requirements/cuda
 export MAX_JOBS=1
 # Make sure release wheels are built for the following architectures
 export TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 8.9 9.0+PTX"
-export VLLM_FA_CMAKE_GPU_ARCHES="80-real;90-real"

 bash tools/check_repo.sh

--- a/.gitignore
+++ b/.gitignore
@ -4,6 +4,9 @@
 # vllm-flash-attn built from source
 vllm/vllm_flash_attn/*

+# triton jit 
+.triton
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
@ -147,7 +150,8 @@ venv.bak/
 # mkdocs documentation
 /site
 docs/argparse
-docs/examples
+docs/examples/*
+!docs/examples/README.md

 # mypy
 .mypy_cache/
@ -203,3 +207,6 @@ shellcheck*/

 # Ignore moe/marlin_moe gen code
 csrc/moe/marlin_moe_wna16/kernel_*
+
+# Ignore ep_kernels_workspace folder
+ep_kernels_workspace/
--- a/.markdownlint.yaml
+++ b/.markdownlint.yaml
@ -0,0 +1,13 @@
+MD007:
+  indent: 4
+MD013: false
+MD024:
+  siblings_only: true
+MD033: false
+MD042: false
+MD045: false
+MD046: false
+MD051: false
+MD052: false
+MD053: false
+MD059: false
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@ -35,12 +35,12 @@ repos:
    exclude: 'csrc/(moe/topk_softmax_kernels.cu|quantization/gguf/(ggml-common.h|dequantize.cuh|vecdotq.cuh|mmq.cuh|mmvq.cuh))|vllm/third_party/.*'
    types_or: [c++, cuda]
    args: [--style=file, --verbose]
- repo: https://github.com/jackdewinter/pymarkdown
-  rev: v0.9.29
+- repo: https://github.com/igorshubovych/markdownlint-cli
+  rev: v0.45.0
  hooks:
-  - id: pymarkdown
+  - id: markdownlint
    exclude: '.*\.inc\.md'
-    args: [fix]
+    stages: [manual] # Only run in CI
 - repo: https://github.com/rhysd/actionlint
  rev: v1.7.7
  hooks:
--- a/.readthedocs.yaml
+++ b/.readthedocs.yaml
@ -7,6 +7,9 @@ build:
  os: ubuntu-22.04
  tools:
    python: "3.12"
+  jobs:
+    post_checkout:
+      - git fetch --unshallow || true

 mkdocs:
  configuration: mkdocs.yaml
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@ -30,7 +30,7 @@ install(CODE "set(CMAKE_INSTALL_LOCAL_ONLY TRUE)" ALL_COMPONENTS)
 # Supported python versions.  These versions will be searched in order, the
 # first match will be selected.  These should be kept in sync with setup.py.
 #
-set(PYTHON_SUPPORTED_VERSIONS "3.9" "3.10" "3.11" "3.12")
+set(PYTHON_SUPPORTED_VERSIONS "3.9" "3.10" "3.11" "3.12", "3.13")

 # Supported AMD GPU architectures.
 set(HIP_SUPPORTED_ARCHS "gfx906;gfx908;gfx90a;gfx942;gfx950;gfx1030;gfx1100;gfx1101;gfx1200;gfx1201")
@ -249,7 +249,6 @@ set(VLLM_EXT_SRC
  "csrc/quantization/gguf/gguf_kernel.cu"
  "csrc/quantization/activation_kernels.cu"
  "csrc/cuda_utils_kernels.cu"
-  "csrc/prepare_inputs/advance_step.cu"
  "csrc/custom_all_reduce.cu"
  "csrc/torch_bindings.cpp")

@ -287,7 +286,6 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
  FetchContent_MakeAvailable(cutlass)

  list(APPEND VLLM_EXT_SRC
-    "csrc/quantization/aqlm/gemm_kernels.cu"
    "csrc/quantization/awq/gemm_kernels.cu"
    "csrc/permute_cols.cu"
    "csrc/quantization/cutlass_w8a8/scaled_mm_entry.cu"
@ -351,20 +349,27 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
    set_gencode_flags_for_srcs(
      SRCS "${MARLIN_TEMPLATE_KERNEL_SRC}"
      CUDA_ARCHS "${MARLIN_ARCHS}")
+    if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8)
+      set_source_files_properties(${MARLIN_TEMPLATE_KERNEL_SRC}
+        PROPERTIES COMPILE_FLAGS "-static-global-template-stub=false")
+    endif()

    list(APPEND VLLM_EXT_SRC ${MARLIN_TEMPLATE_KERNEL_SRC})

    set(MARLIN_SRCS
-       "csrc/quantization/marlin/dense/marlin_cuda_kernel.cu"
       "csrc/quantization/marlin/sparse/marlin_24_cuda_kernel.cu"
-       "csrc/quantization/marlin/qqq/marlin_qqq_gemm_kernel.cu"
       "csrc/quantization/gptq_marlin/gptq_marlin.cu"
       "csrc/quantization/gptq_marlin/gptq_marlin_repack.cu"
       "csrc/quantization/gptq_marlin/awq_marlin_repack.cu")
    set_gencode_flags_for_srcs(
      SRCS "${MARLIN_SRCS}"
      CUDA_ARCHS "${MARLIN_ARCHS}")
+    if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8)
+      set_source_files_properties("csrc/quantization/gptq_marlin/gptq_marlin.cu"
+        PROPERTIES COMPILE_FLAGS "-static-global-template-stub=false")
+    endif()
    list(APPEND VLLM_EXT_SRC "${MARLIN_SRCS}")
+
    message(STATUS "Building Marlin kernels for archs: ${MARLIN_ARCHS}")
  else()
    message(STATUS "Not building Marlin kernels as no compatible archs found"
@ -427,6 +432,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
    set(SRCS
      "csrc/quantization/cutlass_w8a8/scaled_mm_c3x_sm120.cu"
      "csrc/quantization/cutlass_w8a8/c3x/scaled_mm_sm120_fp8.cu"
+      "csrc/quantization/cutlass_w8a8/c3x/scaled_mm_blockwise_sm120_fp8.cu"
    )
    set_gencode_flags_for_srcs(
      SRCS "${SRCS}"
@ -529,6 +535,25 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
    endif()
  endif()

+  # The nvfp4_scaled_mm_sm120 kernels for Geforce Blackwell SM120 require
+  # CUDA 12.8 or later
+  cuda_archs_loose_intersection(FP4_ARCHS "12.0;12.0a" "${CUDA_ARCHS}")
+  if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8 AND FP4_ARCHS)
+    set(SRCS
+      "csrc/quantization/fp4/nvfp4_quant_kernels.cu"
+      "csrc/quantization/fp4/nvfp4_scaled_mm_sm120_kernels.cu")
+    set_gencode_flags_for_srcs(
+      SRCS "${SRCS}"
+      CUDA_ARCHS "${FP4_ARCHS}")
+    list(APPEND VLLM_EXT_SRC "${SRCS}")
+    list(APPEND VLLM_GPU_FLAGS "-DENABLE_NVFP4_SM120=1")
+    message(STATUS "Building NVFP4 for archs: ${FP4_ARCHS}")
+  else()
+    message(STATUS "Not building NVFP4 as no compatible archs were found.")
+    # clear FP4_ARCHS
+    set(FP4_ARCHS)
+  endif()
+
  # FP4 Archs and flags
  cuda_archs_loose_intersection(FP4_ARCHS "10.0a" "${CUDA_ARCHS}")
  if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8 AND FP4_ARCHS)
@ -541,7 +566,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
      SRCS "${SRCS}"
      CUDA_ARCHS "${FP4_ARCHS}")
    list(APPEND VLLM_EXT_SRC "${SRCS}")
-    list(APPEND VLLM_GPU_FLAGS "-DENABLE_NVFP4=1")
+    list(APPEND VLLM_GPU_FLAGS "-DENABLE_NVFP4_SM100=1")
    list(APPEND VLLM_GPU_FLAGS "-DENABLE_CUTLASS_MOE_SM100=1")
    message(STATUS "Building NVFP4 for archs: ${FP4_ARCHS}")
  else()
@ -635,7 +660,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
                     "in CUDA target architectures.")
    endif()
  endif()
-  
+
  cuda_archs_loose_intersection(SCALED_MM_ARCHS "10.0a" "${CUDA_ARCHS}")
  if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8 AND SCALED_MM_ARCHS)
    set(SRCS "csrc/quantization/cutlass_w8a8/moe/blockwise_scaled_group_mm_sm100.cu")
@ -768,6 +793,14 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
  list(APPEND VLLM_MOE_EXT_SRC "csrc/moe/moe_wna16.cu")
 endif()

+if(VLLM_GPU_LANG STREQUAL "CUDA")
+  set(MOE_PERMUTE_SRC
+      "csrc/moe/permute_unpermute_kernels/moe_permute_unpermute_kernel.cu"
+      "csrc/moe/moe_permute_unpermute_op.cu")
+
+  list(APPEND VLLM_MOE_EXT_SRC "${MOE_PERMUTE_SRC}")
+endif()
+
 set_gencode_flags_for_srcs(
  SRCS "${VLLM_MOE_EXT_SRC}"
  CUDA_ARCHS "${CUDA_ARCHS}")
@ -826,6 +859,10 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
    set_gencode_flags_for_srcs(
      SRCS "${MOE_WNAA16_MARLIN_SRC}"
      CUDA_ARCHS "${MARLIN_MOE_ARCHS}")
+    if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8)
+      set_source_files_properties(${MOE_WNAA16_MARLIN_SRC}
+        PROPERTIES COMPILE_FLAGS "-static-global-template-stub=false")
+    endif()

    list(APPEND VLLM_MOE_EXT_SRC ${MOE_WNAA16_MARLIN_SRC})

@ -836,17 +873,6 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
  endif()
 endif()

-if(VLLM_GPU_LANG STREQUAL "CUDA")
-  set(MOE_PERMUTE_SRC
-      "csrc/moe/permute_unpermute_kernels/moe_permute_unpermute_kernel.cu"
-      "csrc/moe/moe_permute_unpermute_op.cu")
-
-  set_gencode_flags_for_srcs(
-    SRCS "${MARLIN_PERMUTE_SRC}"
-    CUDA_ARCHS "${MOE_PERMUTE_ARCHS}")
-
-  list(APPEND VLLM_MOE_EXT_SRC "${MOE_PERMUTE_SRC}")
-endif()
 message(STATUS "Enabling moe extension.")
 define_gpu_extension_target(
  _moe_C
--- a/README.md
+++ b/README.md
@ -1,3 +1,4 @@
+<!-- markdownlint-disable MD001 MD041 -->
 <p align="center">
  <picture>
    <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png">
@ -16,14 +17,16 @@ Easy, fast, and cheap LLM serving for everyone
 ---

 *Latest News* 🔥
+
+- [2025/08] We hosted [vLLM Beijing Meetup](https://mp.weixin.qq.com/s/dgkWg1WFpWGO2jCdTqQHxA) focusing on large-scale LLM deployment! Please find the meetup slides [here](https://drive.google.com/drive/folders/1Pid6NSFLU43DZRi0EaTcPgXsAzDvbBqF) and the recording [here](https://www.chaspark.com/#/live/1166916873711665152).
 - [2025/05] We hosted [NYC vLLM Meetup](https://lu.ma/c1rqyf1f)! Please find the meetup slides [here](https://docs.google.com/presentation/d/1_q_aW_ioMJWUImf1s1YM-ZhjXz8cUeL0IJvaquOYBeA/edit?usp=sharing).
 - [2025/05] vLLM is now a hosted project under PyTorch Foundation! Please find the announcement [here](https://pytorch.org/blog/pytorch-foundation-welcomes-vllm/).
- [2025/04] We hosted [Asia Developer Day](https://www.sginnovate.com/event/limited-availability-morning-evening-slots-remaining-inaugural-vllm-asia-developer-day)! Please find the meetup slides from the vLLM team [here](https://docs.google.com/presentation/d/19cp6Qu8u48ihB91A064XfaXruNYiBOUKrBxAmDOllOo/edit?usp=sharing).
 - [2025/01] We are excited to announce the alpha release of vLLM V1: A major architectural upgrade with 1.7x speedup! Clean code, optimized execution loop, zero-overhead prefix caching, enhanced multimodal support, and more. Please check out our blog post [here](https://blog.vllm.ai/2025/01/27/v1-alpha-release.html).

 <details>
 <summary>Previous News</summary>

+- [2025/04] We hosted [Asia Developer Day](https://www.sginnovate.com/event/limited-availability-morning-evening-slots-remaining-inaugural-vllm-asia-developer-day)! Please find the meetup slides from the vLLM team [here](https://docs.google.com/presentation/d/19cp6Qu8u48ihB91A064XfaXruNYiBOUKrBxAmDOllOo/edit?usp=sharing).
 - [2025/03] We hosted [vLLM x Ollama Inference Night](https://lu.ma/vllm-ollama)! Please find the meetup slides from the vLLM team [here](https://docs.google.com/presentation/d/16T2PDD1YwRnZ4Tu8Q5r6n53c5Lr5c73UV9Vd2_eBo4U/edit?usp=sharing).
 - [2025/03] We hosted [the first vLLM China Meetup](https://mp.weixin.qq.com/s/n77GibL2corAtQHtVEAzfg)! Please find the meetup slides from vLLM team [here](https://docs.google.com/presentation/d/1REHvfQMKGnvz6p3Fd23HhSO4c8j5WPGZV0bKYLwnHyQ/edit?usp=sharing).
 - [2025/03] We hosted [the East Coast vLLM Meetup](https://lu.ma/7mu4k4xx)! Please find the meetup slides [here](https://docs.google.com/presentation/d/1NHiv8EUFF1NLd3fEYODm56nDmL26lEeXCaDgyDlTsRs/edit#slide=id.g31441846c39_0_0).
@ -46,6 +49,7 @@ Easy, fast, and cheap LLM serving for everyone
 </details>

 ---
+
 ## About

 vLLM is a fast and easy-to-use library for LLM inference and serving.
@ -75,6 +79,7 @@ vLLM is flexible and easy to use with:
 - Multi-LoRA support

 vLLM seamlessly supports most popular open-source models on HuggingFace, including:
+
 - Transformer-like LLMs (e.g., Llama)
 - Mixture-of-Expert LLMs (e.g., Mixtral, Deepseek-V2 and V3)
 - Embedding Models (e.g., E5-Mistral)
@ -91,6 +96,7 @@ pip install vllm
 ```

 Visit our [documentation](https://docs.vllm.ai/en/latest/) to learn more.
+
 - [Installation](https://docs.vllm.ai/en/latest/getting_started/installation.html)
 - [Quickstart](https://docs.vllm.ai/en/latest/getting_started/quickstart.html)
 - [List of Supported Models](https://docs.vllm.ai/en/latest/models/supported_models.html)
@ -107,6 +113,7 @@ vLLM is a community project. Our compute resources for development and testing a
 <!-- Note: Please sort them in alphabetical order. -->
 <!-- Note: Please keep these consistent with docs/community/sponsors.md -->
 Cash Donations:
+
 - a16z
 - Dropbox
 - Sequoia Capital
@ -114,6 +121,8 @@ Cash Donations:
 - ZhenFund

 Compute Resources:
+
+- Alibaba Cloud
 - AMD
 - Anyscale
 - AWS
@ -153,7 +162,7 @@ If you use vLLM for your research, please cite our [paper](https://arxiv.org/abs
 ## Contact Us

 <!-- --8<-- [start:contact-us] -->
- For technical questions and feature requests, please use GitHub [Issues](https://github.com/vllm-project/vllm/issues) or [Discussions](https://github.com/vllm-project/vllm/discussions)
+- For technical questions and feature requests, please use GitHub [Issues](https://github.com/vllm-project/vllm/issues)
 - For discussing with fellow users, please use the [vLLM Forum](https://discuss.vllm.ai)
 - For coordinating contributions and development, please use [Slack](https://slack.vllm.ai)
 - For security disclosures, please use GitHub's [Security Advisories](https://github.com/vllm-project/vllm/security/advisories) feature
--- a/RELEASE.md
+++ b/RELEASE.md
@ -60,9 +60,10 @@ Please note: **No feature work allowed for cherry picks**. All PRs that are cons
 Before each release, we perform end-to-end performance validation to ensure no regressions are introduced. This validation uses the [vllm-benchmark workflow](https://github.com/pytorch/pytorch-integration-testing/actions/workflows/vllm-benchmark.yml) on PyTorch CI.

 **Current Coverage:**
+
 * Models: Llama3, Llama4, and Mixtral
 * Hardware: NVIDIA H100 and AMD MI300x
-* *Note: Coverage may change based on new model releases and hardware availability*
+* _Note: Coverage may change based on new model releases and hardware availability_

 **Performance Validation Process:**

@ -71,11 +72,13 @@ Request write access to the [pytorch/pytorch-integration-testing](https://github

 **Step 2: Review Benchmark Setup**
 Familiarize yourself with the benchmark configurations:
+
 * [CUDA setup](https://github.com/pytorch/pytorch-integration-testing/tree/main/vllm-benchmarks/benchmarks/cuda)
 * [ROCm setup](https://github.com/pytorch/pytorch-integration-testing/tree/main/vllm-benchmarks/benchmarks/rocm)

 **Step 3: Run the Benchmark**
 Navigate to the [vllm-benchmark workflow](https://github.com/pytorch/pytorch-integration-testing/actions/workflows/vllm-benchmark.yml) and configure:
+
 * **vLLM branch**: Set to the release branch (e.g., `releases/v0.9.2`)
 * **vLLM commit**: Set to the RC commit hash

--- a/SECURITY.md
+++ b/SECURITY.md
@ -1,13 +1,45 @@
 # Security Policy

-## Reporting a Vulnerability
+## Reporting security issues

-If you believe you have found a security vulnerability in vLLM, we encourage you to let us know right away. We will investigate all legitimate reports and do our best to quickly fix the problem.
+Please report security issues privately using [the vulnerability submission form](https://github.com/vllm-project/vllm/security/advisories/new).

-Please report security issues privately using [the vulnerability submission form](https://github.com/vllm-project/vllm/security/advisories/new). Reports will then be triaged by the [vulnerability management team](https://docs.vllm.ai/en/latest/contributing/vulnerability_management.html).
+## Issue triage

---
+Reports will then be triaged by the [vulnerability management team](https://docs.vllm.ai/en/latest/contributing/vulnerability_management.html).
+
+## Threat model

 Please see the [Security Guide in the vLLM documentation](https://docs.vllm.ai/en/latest/usage/security.html) for more information on vLLM's security assumptions and recommendations.

 Please see [PyTorch's Security Policy](https://github.com/pytorch/pytorch/blob/main/SECURITY.md) for more information and recommendations on how to securely interact with models.
+
+## Issue severity
+
+We will determine the risk of each issue, taking into account our experience dealing with past issues, versions affected, common defaults, and use cases. We use the following severity categories:
+
+### CRITICAL Severity
+
+Vulnerabilities that allow remote attackers to execute arbitrary code, take full control of the system, or significantly compromise confidentiality, integrity, or availability without any interaction or privileges needed, examples include remote code execution via network, deserialization issues that allow exploit chains. Generally those issues which are rated as CVSS  ≥ 9.0.
+
+### HIGH Severity
+
+Serious security flaws that allow elevated impact—like RCE in specific, limited contexts or significant data loss—but require advanced conditions or some trust, examples include RCE in advanced deployment modes (e.g. multi-node), or high impact issues where some sort of privileged network access is required. These issues typically have CVSS scores between 7.0 and 8.9
+
+### MODERATE Severity
+
+Vulnerabilities that cause denial of service or partial disruption, but do not allow arbitrary code execution or data breach and have limited impact. These issues have a CVSS rating between 4.0 and 6.9
+
+### LOW Severity
+
+Minor issues such as informational disclosures, logging errors, non-exploitable flaws, or weaknesses that require local or high-privilege access and offer negligible impact. Examples include side channel attacks or hash collisions. These issues often have CVSS scores less than 4.0
+
+## Prenotification policy
+
+For certain security issues of CRITICAL, HIGH, or MODERATE severity level, we may prenotify certain organizations or vendors that ship vLLM. The purpose of this prenotification is to allow for a coordinated release of fixes for severe issues.
+
+* This prenotification will be in the form of a private email notification. It may also include adding security contacts to the GitHub security advisory, typically a few days before release.
+
+* If you wish to be added to the prenotification group, please send an email copying all the members of the [vulnerability management team](https://docs.vllm.ai/en/latest/contributing/vulnerability_management.html). Each vendor contact will be analyzed on a case-by-case basis.
+
+* We may withdraw organizations from receiving future prenotifications if they release fixes or any other information about issues before they are public. Group membership may also change based on policy refinements for who may be included.
--- a/benchmarks/README.md
+++ b/benchmarks/README.md
@ -4,7 +4,7 @@ This README guides you through running benchmark tests with the extensive
 datasets supported on vLLM. It’s a living document, updated as new features and datasets
 become available.

-**Dataset Overview**
+## Dataset Overview

 <table style="width:100%; border-collapse: collapse;">
  <thead>
@ -22,6 +22,25 @@ become available.
      <td style="text-align: center;">✅</td>
      <td><code>wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json</code></td>
    </tr>
+    <tr>
+      <td><strong>ShareGPT4V (Image)</strong></td>
+      <td style="text-align: center;">✅</td>
+      <td style="text-align: center;">✅</td>
+      <td>
+        <code>wget https://huggingface.co/datasets/Lin-Chen/ShareGPT4V/blob/main/sharegpt4v_instruct_gpt4-vision_cap100k.json</code>
+        <br>
+        <div>Note that the images need to be downloaded separately. For example, to download COCO's 2017 Train images:</div>
+        <code>wget http://images.cocodataset.org/zips/train2017.zip</code>
+      </td>
+    </tr>
+        <tr>
+      <td><strong>ShareGPT4Video (Video)</strong></td>
+      <td style="text-align: center;">✅</td>
+      <td style="text-align: center;">✅</td>
+      <td>
+        <code>git clone https://huggingface.co/datasets/ShareGPT4Video/ShareGPT4Video</code>
+      </td>
+    </tr>
    <tr>
      <td><strong>BurstGPT</strong></td>
      <td style="text-align: center;">✅</td>
@ -29,7 +48,7 @@ become available.
      <td><code>wget https://github.com/HPMLL/BurstGPT/releases/download/v1.1/BurstGPT_without_fails_2.csv</code></td>
    </tr>
    <tr>
-      <td><strong>Sonnet</strong></td>
+      <td><strong>Sonnet (deprecated)</strong></td>
      <td style="text-align: center;">✅</td>
      <td style="text-align: center;">✅</td>
      <td>Local file: <code>benchmarks/sonnet.txt</code></td>
@ -40,6 +59,12 @@ become available.
      <td style="text-align: center;">✅</td>
      <td><code>synthetic</code></td>
    </tr>
+    <tr>
+      <td><strong>Prefix Repetition</strong></td>
+      <td style="text-align: center;">✅</td>
+      <td style="text-align: center;">✅</td>
+      <td><code>synthetic</code></td>
+    </tr>
    <tr>
      <td><strong>HuggingFace-VisionArena</strong></td>
      <td style="text-align: center;">✅</td>
@ -81,16 +106,17 @@ become available.

 **Note**: HuggingFace dataset's `dataset-name` should be set to `hf`

---
+## 🚀 Example - Online Benchmark
+
 <details>
-<summary><b>🚀 Example - Online Benchmark</b></summary>
+<summary>Show more</summary>

 <br/>

 First start serving your model

 ```bash
-vllm serve NousResearch/Hermes-3-Llama-3.1-8B --disable-log-requests
+vllm serve NousResearch/Hermes-3-Llama-3.1-8B
 ```

 Then run the benchmarking script
@ -98,7 +124,7 @@ Then run the benchmarking script
 ```bash
 # download dataset
 # wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json
-python3 vllm/benchmarks/benchmark_serving.py \
+vllm bench serve \
  --backend vllm \
  --model NousResearch/Hermes-3-Llama-3.1-8B \
  --endpoint /v1/completions \
@ -109,48 +135,48 @@ python3 vllm/benchmarks/benchmark_serving.py \

 If successful, you will see the following output

-```
+```text
 ============ Serving Benchmark Result ============
-Successful requests:                     10        
-Benchmark duration (s):                  5.78      
-Total input tokens:                      1369      
-Total generated tokens:                  2212      
-Request throughput (req/s):              1.73      
-Output token throughput (tok/s):         382.89    
-Total Token throughput (tok/s):          619.85    
+Successful requests:                     10
+Benchmark duration (s):                  5.78
+Total input tokens:                      1369
+Total generated tokens:                  2212
+Request throughput (req/s):              1.73
+Output token throughput (tok/s):         382.89
+Total Token throughput (tok/s):          619.85
 ---------------Time to First Token----------------
-Mean TTFT (ms):                          71.54     
-Median TTFT (ms):                        73.88     
-P99 TTFT (ms):                           79.49     
+Mean TTFT (ms):                          71.54
+Median TTFT (ms):                        73.88
+P99 TTFT (ms):                           79.49
 -----Time per Output Token (excl. 1st token)------
-Mean TPOT (ms):                          7.91      
-Median TPOT (ms):                        7.96      
-P99 TPOT (ms):                           8.03      
+Mean TPOT (ms):                          7.91
+Median TPOT (ms):                        7.96
+P99 TPOT (ms):                           8.03
 ---------------Inter-token Latency----------------
-Mean ITL (ms):                           7.74      
-Median ITL (ms):                         7.70      
-P99 ITL (ms):                            8.39      
+Mean ITL (ms):                           7.74
+Median ITL (ms):                         7.70
+P99 ITL (ms):                            8.39
 ==================================================
 ```

-**Custom Dataset**
+### Custom Dataset

 If the dataset you want to benchmark is not supported yet in vLLM, even then you can benchmark on it using `CustomDataset`. Your data needs to be in `.jsonl` format and needs to have "prompt" field per entry, e.g., data.jsonl

-```
+```json
 {"prompt": "What is the capital of India?"}
 {"prompt": "What is the capital of Iran?"}
 {"prompt": "What is the capital of China?"}
-``` 
+```

 ```bash
 # start server
-VLLM_USE_V1=1 vllm serve meta-llama/Llama-3.1-8B-Instruct --disable-log-requests
+VLLM_USE_V1=1 vllm serve meta-llama/Llama-3.1-8B-Instruct
 ```

 ```bash
 # run benchmarking script
-python3 benchmarks/benchmark_serving.py --port 9001 --save-result --save-detailed \
+vllm bench serve --port 9001 --save-result --save-detailed \
  --backend vllm \
  --model meta-llama/Llama-3.1-8B-Instruct \
  --endpoint /v1/completions \
@ -166,16 +192,17 @@ python3 benchmarks/benchmark_serving.py --port 9001 --save-result --save-detaile

 You can skip applying chat template if your data already has it by using `--custom-skip-chat-template`.

-**VisionArena Benchmark for Vision Language Models**
+### VisionArena Benchmark for Vision Language Models

 ```bash
 # need a model with vision capability here
-vllm serve Qwen/Qwen2-VL-7B-Instruct --disable-log-requests
+vllm serve Qwen/Qwen2-VL-7B-Instruct
 ```

 ```bash
-python3 vllm/benchmarks/benchmark_serving.py \
+vllm bench serve \
  --backend openai-chat \
+  --endpoint-type openai-chat \
  --model Qwen/Qwen2-VL-7B-Instruct \
  --endpoint /v1/chat/completions \
  --dataset-name hf \
@ -184,7 +211,7 @@ python3 vllm/benchmarks/benchmark_serving.py \
  --num-prompts 1000
 ```

-**InstructCoder Benchmark with Speculative Decoding**
+### InstructCoder Benchmark with Speculative Decoding

 ``` bash
 VLLM_USE_V1=1 vllm serve meta-llama/Meta-Llama-3-8B-Instruct \
@ -194,24 +221,25 @@ VLLM_USE_V1=1 vllm serve meta-llama/Meta-Llama-3-8B-Instruct \
 ```

 ``` bash
-python3 benchmarks/benchmark_serving.py \
+vllm bench serve \
    --model meta-llama/Meta-Llama-3-8B-Instruct \
    --dataset-name hf \
    --dataset-path likaixin/InstructCoder \
    --num-prompts 2048
 ```

-**Other HuggingFaceDataset Examples**
+### Other HuggingFaceDataset Examples

 ```bash
-vllm serve Qwen/Qwen2-VL-7B-Instruct --disable-log-requests
+vllm serve Qwen/Qwen2-VL-7B-Instruct
 ```

-**`lmms-lab/LLaVA-OneVision-Data`**
+`lmms-lab/LLaVA-OneVision-Data`:

 ```bash
-python3 vllm/benchmarks/benchmark_serving.py \
+vllm bench serve \
  --backend openai-chat \
+  --endpoint-type openai-chat \
  --model Qwen/Qwen2-VL-7B-Instruct \
  --endpoint /v1/chat/completions \
  --dataset-name hf \
@ -221,11 +249,12 @@ python3 vllm/benchmarks/benchmark_serving.py \
  --num-prompts 10
 ```

-**`Aeala/ShareGPT_Vicuna_unfiltered`**
+`Aeala/ShareGPT_Vicuna_unfiltered`:

 ```bash
-python3 vllm/benchmarks/benchmark_serving.py \
+vllm bench serve \
  --backend openai-chat \
+  --endpoint-type openai-chat \
  --model Qwen/Qwen2-VL-7B-Instruct \
  --endpoint /v1/chat/completions \
  --dataset-name hf \
@ -234,10 +263,10 @@ python3 vllm/benchmarks/benchmark_serving.py \
  --num-prompts 10
 ```

-**`AI-MO/aimo-validation-aime`**
+`AI-MO/aimo-validation-aime`:

 ``` bash
-python3 vllm/benchmarks/benchmark_serving.py \
+vllm bench serve \
    --model Qwen/QwQ-32B \
    --dataset-name hf \
    --dataset-path AI-MO/aimo-validation-aime \
@ -245,23 +274,23 @@ python3 vllm/benchmarks/benchmark_serving.py \
    --seed 42
 ```

-**`philschmid/mt-bench`**
+`philschmid/mt-bench`:

 ``` bash
-python3 vllm/benchmarks/benchmark_serving.py \
+vllm bench serve \
    --model Qwen/QwQ-32B \
    --dataset-name hf \
    --dataset-path philschmid/mt-bench \
    --num-prompts 80
 ```

-**Running With Sampling Parameters**
+### Running With Sampling Parameters

 When using OpenAI-compatible backends such as `vllm`, optional sampling
 parameters can be specified. Example client command:

 ```bash
-python3 vllm/benchmarks/benchmark_serving.py \
+vllm bench serve \
  --backend vllm \
  --model NousResearch/Hermes-3-Llama-3.1-8B \
  --endpoint /v1/completions \
@ -273,30 +302,34 @@ python3 vllm/benchmarks/benchmark_serving.py \
  --num-prompts 10
 ```

-**Running With Ramp-Up Request Rate**
+### Running With Ramp-Up Request Rate

 The benchmark tool also supports ramping up the request rate over the
 duration of the benchmark run. This can be useful for stress testing the
 server or finding the maximum throughput that it can handle, given some latency budget.

 Two ramp-up strategies are supported:
+
 - `linear`: Increases the request rate linearly from a start value to an end value.
 - `exponential`: Increases the request rate exponentially.

 The following arguments can be used to control the ramp-up:
+
 - `--ramp-up-strategy`: The ramp-up strategy to use (`linear` or `exponential`).
 - `--ramp-up-start-rps`: The request rate at the beginning of the benchmark.
 - `--ramp-up-end-rps`: The request rate at the end of the benchmark.

 </details>

+## 📈 Example - Offline Throughput Benchmark
+
 <details>
-<summary><b>📈 Example - Offline Throughput Benchmark</b></summary>
+<summary>Show more</summary>

 <br/>

 ```bash
-python3 vllm/benchmarks/benchmark_throughput.py \
+vllm bench throughput \
  --model NousResearch/Hermes-3-Llama-3.1-8B \
  --dataset-name sonnet \
  --dataset-path vllm/benchmarks/sonnet.txt \
@ -305,16 +338,16 @@ python3 vllm/benchmarks/benchmark_throughput.py \

 If successful, you will see the following output

-```
+```text
 Throughput: 7.15 requests/s, 4656.00 total tokens/s, 1072.15 output tokens/s
 Total num prompt tokens:  5014
 Total num output tokens:  1500
 ```

-**VisionArena Benchmark for Vision Language Models**
+### VisionArena Benchmark for Vision Language Models

-``` bash
-python3 vllm/benchmarks/benchmark_throughput.py \
+```bash
+vllm bench throughput \
  --model Qwen/Qwen2-VL-7B-Instruct \
  --backend vllm-chat \
  --dataset-name hf \
@ -325,18 +358,18 @@ python3 vllm/benchmarks/benchmark_throughput.py \

 The `num prompt tokens` now includes image token counts

-```
+```text
 Throughput: 2.55 requests/s, 4036.92 total tokens/s, 326.90 output tokens/s
 Total num prompt tokens:  14527
 Total num output tokens:  1280
 ```

-**InstructCoder Benchmark with Speculative Decoding**
+### InstructCoder Benchmark with Speculative Decoding

 ``` bash
 VLLM_WORKER_MULTIPROC_METHOD=spawn \
 VLLM_USE_V1=1 \
-python3 vllm/benchmarks/benchmark_throughput.py \
+vllm bench throughput \
    --dataset-name=hf \
    --dataset-path=likaixin/InstructCoder \
    --model=meta-llama/Meta-Llama-3-8B-Instruct \
@ -349,18 +382,18 @@ python3 vllm/benchmarks/benchmark_throughput.py \
    "prompt_lookup_min": 2}'
 ```

-```
+```text
 Throughput: 104.77 requests/s, 23836.22 total tokens/s, 10477.10 output tokens/s
 Total num prompt tokens:  261136
 Total num output tokens:  204800
 ```

-**Other HuggingFaceDataset Examples**
+### Other HuggingFaceDataset Examples

-**`lmms-lab/LLaVA-OneVision-Data`**
+`lmms-lab/LLaVA-OneVision-Data`:

 ```bash
-python3 vllm/benchmarks/benchmark_throughput.py \
+vllm bench throughput \
  --model Qwen/Qwen2-VL-7B-Instruct \
  --backend vllm-chat \
  --dataset-name hf \
@ -370,10 +403,10 @@ python3 vllm/benchmarks/benchmark_throughput.py \
  --num-prompts 10
 ```

-**`Aeala/ShareGPT_Vicuna_unfiltered`**
+`Aeala/ShareGPT_Vicuna_unfiltered`:

 ```bash
-python3 vllm/benchmarks/benchmark_throughput.py \
+vllm bench throughput \
  --model Qwen/Qwen2-VL-7B-Instruct \
  --backend vllm-chat \
  --dataset-name hf \
@ -382,10 +415,10 @@ python3 vllm/benchmarks/benchmark_throughput.py \
  --num-prompts 10
 ```

-**`AI-MO/aimo-validation-aime`**
+`AI-MO/aimo-validation-aime`:

 ```bash
-python3 benchmarks/benchmark_throughput.py \
+vllm bench throughput \
  --model Qwen/QwQ-32B \
  --backend vllm \
  --dataset-name hf \
@ -394,12 +427,12 @@ python3 benchmarks/benchmark_throughput.py \
  --num-prompts 10
 ```

-**Benchmark with LoRA Adapters**
+Benchmark with LoRA adapters:

 ``` bash
 # download dataset
 # wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json
-python3 vllm/benchmarks/benchmark_throughput.py \
+vllm bench throughput \
  --model meta-llama/Llama-2-7b-hf \
  --backend vllm \
  --dataset_path <your data path>/ShareGPT_V3_unfiltered_cleaned_split.json \
@ -413,20 +446,22 @@ python3 vllm/benchmarks/benchmark_throughput.py \

 </details>

+## 🛠️ Example - Structured Output Benchmark
+
 <details>
-<summary><b>🛠️ Example - Structured Output Benchmark</b></summary>
+<summary>Show more</summary>

 <br/>

 Benchmark the performance of structured output generation (JSON, grammar, regex).

-**Server Setup**
+### Server Setup

 ```bash
-vllm serve NousResearch/Hermes-3-Llama-3.1-8B --disable-log-requests
+vllm serve NousResearch/Hermes-3-Llama-3.1-8B
 ```

-**JSON Schema Benchmark**
+### JSON Schema Benchmark

 ```bash
 python3 benchmarks/benchmark_serving_structured_output.py \
@ -438,7 +473,7 @@ python3 benchmarks/benchmark_serving_structured_output.py \
  --num-prompts 1000
 ```

-**Grammar-based Generation Benchmark**
+### Grammar-based Generation Benchmark

 ```bash
 python3 benchmarks/benchmark_serving_structured_output.py \
@ -450,7 +485,7 @@ python3 benchmarks/benchmark_serving_structured_output.py \
  --num-prompts 1000
 ```

-**Regex-based Generation Benchmark**
+### Regex-based Generation Benchmark

 ```bash
 python3 benchmarks/benchmark_serving_structured_output.py \
@ -461,7 +496,7 @@ python3 benchmarks/benchmark_serving_structured_output.py \
  --num-prompts 1000
 ```

-**Choice-based Generation Benchmark**
+### Choice-based Generation Benchmark

 ```bash
 python3 benchmarks/benchmark_serving_structured_output.py \
@ -472,7 +507,7 @@ python3 benchmarks/benchmark_serving_structured_output.py \
  --num-prompts 1000
 ```

-**XGrammar Benchmark Dataset**
+### XGrammar Benchmark Dataset

 ```bash
 python3 benchmarks/benchmark_serving_structured_output.py \
@ -485,14 +520,16 @@ python3 benchmarks/benchmark_serving_structured_output.py \

 </details>

+## 📚 Example - Long Document QA Benchmark
+
 <details>
-<summary><b>📚 Example - Long Document QA Benchmark</b></summary>
+<summary>Show more</summary>

 <br/>

 Benchmark the performance of long document question-answering with prefix caching.

-**Basic Long Document QA Test**
+### Basic Long Document QA Test

 ```bash
 python3 benchmarks/benchmark_long_document_qa_throughput.py \
@ -504,7 +541,7 @@ python3 benchmarks/benchmark_long_document_qa_throughput.py \
  --repeat-count 5
 ```

-**Different Repeat Modes**
+### Different Repeat Modes

 ```bash
 # Random mode (default) - shuffle prompts randomly
@ -537,14 +574,16 @@ python3 benchmarks/benchmark_long_document_qa_throughput.py \

 </details>

+## 🗂️ Example - Prefix Caching Benchmark
+
 <details>
-<summary><b>🗂️ Example - Prefix Caching Benchmark</b></summary>
+<summary>Show more</summary>

 <br/>

 Benchmark the efficiency of automatic prefix caching.

-**Fixed Prompt with Prefix Caching**
+### Fixed Prompt with Prefix Caching

 ```bash
 python3 benchmarks/benchmark_prefix_caching.py \
@ -555,7 +594,7 @@ python3 benchmarks/benchmark_prefix_caching.py \
  --input-length-range 128:256
 ```

-**ShareGPT Dataset with Prefix Caching**
+### ShareGPT Dataset with Prefix Caching

 ```bash
 # download dataset
@ -570,16 +609,32 @@ python3 benchmarks/benchmark_prefix_caching.py \
  --input-length-range 128:256
 ```

+### Prefix Repetition Dataset
+
+```bash
+vllm bench serve \
+  --backend openai \
+  --model meta-llama/Llama-2-7b-chat-hf \
+  --dataset-name prefix_repetition \
+  --num-prompts 100 \
+  --prefix-repetition-prefix-len 512 \
+  --prefix-repetition-suffix-len 128 \
+  --prefix-repetition-num-prefixes 5 \
+  --prefix-repetition-output-len 128
+```
+
 </details>

+## ⚡ Example - Request Prioritization Benchmark
+
 <details>
-<summary><b>⚡ Example - Request Prioritization Benchmark</b></summary>
+<summary>Show more</summary>

 <br/>

 Benchmark the performance of request prioritization in vLLM.

-**Basic Prioritization Test**
+### Basic Prioritization Test

 ```bash
 python3 benchmarks/benchmark_prioritization.py \
@ -590,7 +645,7 @@ python3 benchmarks/benchmark_prioritization.py \
  --scheduling-policy priority
 ```

-**Multiple Sequences per Prompt**
+### Multiple Sequences per Prompt

 ```bash
 python3 benchmarks/benchmark_prioritization.py \
@ -603,3 +658,68 @@ python3 benchmarks/benchmark_prioritization.py \
 ```

 </details>
+
+## 👁️ Example - Multi-Modal Benchmark
+
+<details>
+<summary>Show more</summary>
+
+<br/>
+
+Benchmark the performance of multi-modal requests in vLLM.
+
+### Images (ShareGPT4V)
+
+Start vLLM:
+
+```bash
+python -m vllm.entrypoints.openai.api_server \
+  --model Qwen/Qwen2.5-VL-7B-Instruct \
+  --dtype bfloat16 \
+  --limit-mm-per-prompt '{"image": 1}' \
+  --allowed-local-media-path /path/to/sharegpt4v/images
+```
+
+Send requests with images:
+
+```bash
+python benchmarks/benchmark_serving.py \
+  --backend openai-chat \
+  --model Qwen/Qwen2.5-VL-7B-Instruct \
+  --dataset-name sharegpt \
+  --dataset-path /path/to/ShareGPT4V/sharegpt4v_instruct_gpt4-vision_cap100k.json \
+  --num-prompts 100 \
+  --save-result \
+  --result-dir ~/vllm_benchmark_results \
+  --save-detailed \
+  --endpoint /v1/chat/completion
+```
+
+### Videos (ShareGPT4Video)
+
+Start vLLM:
+
+```bash
+python -m vllm.entrypoints.openai.api_server \
+  --model Qwen/Qwen2.5-VL-7B-Instruct \
+  --dtype bfloat16 \
+  --limit-mm-per-prompt '{"video": 1}' \
+  --allowed-local-media-path /path/to/sharegpt4video/videos
+```
+
+Send requests with videos:
+
+```bash
+python benchmarks/benchmark_serving.py \
+  --backend openai-chat \
+  --model Qwen/Qwen2.5-VL-7B-Instruct \
+  --dataset-name sharegpt \
+  --dataset-path /path/to/ShareGPT4Video/llava_v1_5_mix665k_with_video_chatgpt72k_share4video28k.json \
+  --num-prompts 100 \
+  --save-result \
+  --result-dir ~/vllm_benchmark_results \
+  --save-detailed \
+  --endpoint /v1/chat/completion
+```
+
+</details>
--- a/benchmarks/auto_tune/README.md
+++ b/benchmarks/auto_tune/README.md
@ -3,6 +3,7 @@
 This script automates the process of finding the optimal server parameter combination (`max-num-seqs` and `max-num-batched-tokens`) to maximize throughput for a vLLM server. It also supports additional constraints such as E2E latency and prefix cache hit rate.

 ## Table of Contents
+
 - [Prerequisites](#prerequisites)
 - [Configuration](#configuration)
 - [How to Run](#how-to-run)
@ -39,6 +40,7 @@ You must set the following variables at the top of the script before execution.
 | `DOWNLOAD_DIR` | **Required.** Directory to download and load model weights from. | `""` (default download path) |
 | `INPUT_LEN` | **Required.** Request input length. | `4000` |
 | `OUTPUT_LEN` | **Required.** Request output length. | `16` |
+| `MAX_MODEL_LEN` | **Required.** Max model length. | `4096` |
 | `MIN_CACHE_HIT_PCT` | Prefix cache hit rate in percentage (0-100). Set to `0` to disable. | `60` |
 | `MAX_LATENCY_ALLOWED_MS` | The maximum allowed P99 end-to-end latency in milliseconds. Set to a very large number (e.g., `100000000000`) to effectively ignore the latency constraint. | `500` |
 | `NUM_SEQS_LIST` | A space-separated string of `max-num-seqs` values to test. | `"128 256"` |
@ -51,7 +53,7 @@ You must set the following variables at the top of the script before execution.
 1. **Configure**: Edit the script and set the variables in the [Configuration](#configuration) section.
 2. **Execute**: Run the script. Since the process can take a long time, it is highly recommended to use a terminal multiplexer like `tmux` or `screen` to prevent the script from stopping if your connection is lost.

-```
+```bash
 cd <FOLDER_OF_THIS_SCRIPT>
 bash auto_tune.sh
 ```
@ -63,34 +65,40 @@ bash auto_tune.sh
 Here are a few examples of how to configure the script for different goals:

 ### 1. Maximize Throughput (No Latency Constraint)
+
 - **Goal**: Find the best `max-num-seqs` and `max-num-batched-tokens` to get the highest possible throughput for 1800 input tokens and 20 output tokens.
 - **Configuration**:

 ```bash
 INPUT_LEN=1800
 OUTPUT_LEN=20
+MAX_MODEL_LEN=2048
 MIN_CACHE_HIT_PCT=0
 MAX_LATENCY_ALLOWED_MS=100000000000 # A very large number
 ```

 #### 2. Maximize Throughput with a Latency Requirement
+
 - **Goal**: Find the best server parameters when P99 end-to-end latency must be below 500ms.
 - **Configuration**:

 ```bash
 INPUT_LEN=1800
 OUTPUT_LEN=20
+MAX_MODEL_LEN=2048
 MIN_CACHE_HIT_PCT=0
 MAX_LATENCY_ALLOWED_MS=500
 ```

 #### 3. Maximize Throughput with Prefix Caching and Latency Requirements
+
 - **Goal**: Find the best server parameters assuming a 60% prefix cache hit rate and a latency requirement of 500ms.
 - **Configuration**:

 ```bash
 INPUT_LEN=1800
 OUTPUT_LEN=20
+MAX_MODEL_LEN=2048
 MIN_CACHE_HIT_PCT=60
 MAX_LATENCY_ALLOWED_MS=500
 ```
@ -101,11 +109,11 @@ After the script finishes, you will find the results in a new, timestamped direc

 - **Log Files**: The directory (`$BASE/auto-benchmark/YYYY_MM_DD_HH_MM/`) contains detailed logs for each run:
    - `vllm_log_...txt`: The log output from the vLLM server for each parameter combination.
-    - `bm_log_...txt`: The log output from the `benchmark_serving.py` script for each benchmark run.
+    - `bm_log_...txt`: The log output from the `vllm bench serve` command for each benchmark run.

 - **Final Result Summary**: A file named `result.txt` is created in the log directory. It contains a summary of each tested combination and concludes with the overall best parameters found.

-```
+```text
 # Example result.txt content
 hash:a1b2c3d4...
 max_num_seqs: 128, max_num_batched_tokens: 2048, request_rate: 10.0, e2el: 450.5, throughput: 9.8, goodput: 9.8
--- a/benchmarks/auto_tune/auto_tune.sh
+++ b/benchmarks/auto_tune/auto_tune.sh
@ -1,16 +1,18 @@
 #!/bin/bash

-# This script aims to tune the best server parameter combinations to maximize throughput for given requirement. 
+# This script aims to tune the best server parameter combinations to maximize throughput for given requirement.
 # See details in README (benchmarks/auto_tune/README.md).

 TAG=$(date +"%Y_%m_%d_%H_%M")
-BASE=""
+SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
+BASE="$SCRIPT_DIR/../../.."
 MODEL="meta-llama/Llama-3.1-8B-Instruct"
 SYSTEM="TPU"
 TP=1
 DOWNLOAD_DIR=""
 INPUT_LEN=4000
 OUTPUT_LEN=16
+MAX_MODEL_LEN=4096
 MIN_CACHE_HIT_PCT=0
 MAX_LATENCY_ALLOWED_MS=100000000000
 NUM_SEQS_LIST="128 256"
@ -36,10 +38,18 @@ current_hash=$(git rev-parse HEAD)
 echo "hash:$current_hash" >> "$RESULT"
 echo "current_hash: $current_hash"

+TOTAL_LEN=$((INPUT_LEN + OUTPUT_LEN))
+RED='\033[0;31m'
+if (( TOTAL_LEN > MAX_MODEL_LEN )); then
+    echo -e "${RED}FAILED: INPUT_LEN($INPUT_LEN) + OUTPUT_LEN($OUTPUT_LEN) = $TOTAL_LEN, which is > MAX_MODEL_LEN = $MAX_MODEL_LEN.\033[0m" >&2
+    exit 1
+fi
+
 best_throughput=0
 best_max_num_seqs=0
 best_num_batched_tokens=0
 best_goodput=0
+best_request_rate=0

 start_server() {
    local gpu_memory_utilization=$1
@ -47,26 +57,42 @@ start_server() {
    local max_num_batched_tokens=$3
    local vllm_log=$4
    local profile_dir=$5
-    
-    pkill -f vllm

-    VLLM_USE_V1=1 VLLM_SERVER_DEV_MODE=1 VLLM_TORCH_PROFILER_DIR=$profile_dir vllm serve $MODEL \
-        --disable-log-requests \
-        --port 8004 \
-        --gpu-memory-utilization $gpu_memory_utilization \
-        --max-num-seqs $max_num_seqs \
-        --max-num-batched-tokens $max_num_batched_tokens \
-        --tensor-parallel-size $TP \
-        --enable-prefix-caching \
-        --load-format dummy \
-        --download-dir "$DOWNLOAD_DIR" \
-        --max-model-len $(( INPUT_LEN+OUTPUT_LEN )) > "$vllm_log" 2>&1 &
+    pkill -if vllm
+
+    # Define the common arguments as a bash array.
+    # Each argument and its value are separate elements.
+    local common_args_array=(
+        "$MODEL"
+        "--disable-log-requests"
+        "--port" "8004"
+        "--gpu-memory-utilization" "$gpu_memory_utilization"
+        "--max-num-seqs" "$max_num_seqs"
+        "--max-num-batched-tokens" "$max_num_batched_tokens"
+        "--tensor-parallel-size" "$TP"
+        "--enable-prefix-caching"
+        "--load-format" "dummy"
+        "--download-dir" "$DOWNLOAD_DIR"
+        "--max-model-len" "$MAX_MODEL_LEN"
+    )
+
+    # Use the array expansion "${common_args_array[@]}"
+    # This correctly passes each element as a separate argument.
+    if [[ -n "$profile_dir" ]]; then
+        # Start server with profiling enabled
+        VLLM_USE_V1=1 VLLM_SERVER_DEV_MODE=1 VLLM_TORCH_PROFILER_DIR=$profile_dir \
+            vllm serve "${common_args_array[@]}" > "$vllm_log" 2>&1 &
+    else
+        # Start server without profiling
+        VLLM_USE_V1=1 VLLM_SERVER_DEV_MODE=1 \
+            vllm serve "${common_args_array[@]}" > "$vllm_log" 2>&1 &
+    fi

    # wait for 10 minutes...
    server_started=0
-    for i in {1..60}; do  
+    for i in {1..60}; do
        RESPONSE=$(curl -s -X GET "http://0.0.0.0:8004/health" -w "%{http_code}" -o /dev/stdout)
-        STATUS_CODE=$(echo "$RESPONSE" | tail -n 1) 
+        STATUS_CODE=$(echo "$RESPONSE" | tail -n 1)
        if [[ "$STATUS_CODE" -eq 200 ]]; then
            server_started=1
            break
@ -74,6 +100,7 @@ start_server() {
            sleep 10
        fi
    done
+
    if (( ! server_started )); then
        echo "server did not start within 10 minutes. Please check server log at $vllm_log".
        return 1
@ -82,37 +109,20 @@ start_server() {
    fi
 }

-update_best_profile() {
-    local profile_dir=$1
-    local profile_index=$2
-    sorted_paths=($(find "$profile_dir" -maxdepth 1 -not -path "$profile_dir" | sort))
-    selected_profile_file=
-    if [[ "$SYSTEM" == "TPU" ]]; then
-        selected_profile_file="${sorted_paths[$profile_index]}/*.xplane.pb"
-    fi 
-    if [[ "$SYSTEM" == "GPU" ]]; then
-        selected_profile_file="${sorted_paths[$profile_index]}"
-    fi 
-    rm -f $PROFILE_PATH/*
-    cp $selected_profile_file $PROFILE_PATH
-}
-
 run_benchmark() {
    local max_num_seqs=$1
    local max_num_batched_tokens=$2
    local gpu_memory_utilization=$3
    echo "max_num_seq: $max_num_seqs, max_num_batched_tokens: $max_num_batched_tokens"
    local vllm_log="$LOG_FOLDER/vllm_log_${max_num_seqs}_${max_num_batched_tokens}.txt"
-    local profile_dir="$LOG_FOLDER/profile_${max_num_seqs}_${max_num_batched_tokens}"
    echo "vllm_log: $vllm_log"
    echo
    rm -f $vllm_log
-    mkdir -p $profile_dir
-    pkill -f vllm
-    local profile_index=0
+    pkill -if vllm

    echo "starting server..."
-    start_server $gpu_memory_utilization $max_num_seqs $max_num_batched_tokens $vllm_log $profile_dir
+    # Call start_server without a profile_dir to avoid profiling overhead
+    start_server $gpu_memory_utilization $max_num_seqs $max_num_batched_tokens $vllm_log ""
    result=$?
    if [[ "$result" -eq 1 ]]; then
        echo "server failed to start. gpu_memory_utilization:$gpu_memory_utilization, max_num_seqs:$max_num_seqs, max_num_batched_tokens: $max_num_batched_tokens"
@ -120,14 +130,15 @@ run_benchmark() {
        echo "server started."
    fi
    echo
-    
+
    echo "run benchmark test..."
    meet_latency_requirement=0
    # get a basic qps by using request-rate inf
    bm_log="$LOG_FOLDER/bm_log_${max_num_seqs}_${max_num_batched_tokens}_requestrate_inf.txt"
    prefix_len=$(( INPUT_LEN * MIN_CACHE_HIT_PCT / 100 ))
-adjusted_input_len=$(( INPUT_LEN - prefix_len ))
-    python3 benchmarks/benchmark_serving.py \
+    adjusted_input_len=$(( INPUT_LEN - prefix_len ))
+    # --profile flag is removed from this call
+    vllm bench serve \
        --backend vllm \
        --model $MODEL  \
        --dataset-name random \
@ -140,8 +151,7 @@ adjusted_input_len=$(( INPUT_LEN - prefix_len ))
        --goodput e2el:$MAX_LATENCY_ALLOWED_MS \
        --num-prompts 1000 \
        --random-prefix-len $prefix_len \
-        --port 8004 \
-        --profile &> "$bm_log"
+        --port 8004 &> "$bm_log"
    throughput=$(grep "Request throughput (req/s):" "$bm_log" | sed 's/[^0-9.]//g')
    e2el=$(grep "P99 E2EL (ms):" "$bm_log" | awk '{print $NF}')
    goodput=$(grep "Request goodput (req/s):" "$bm_log" | sed 's/[^0-9.]//g')
@ -155,12 +165,11 @@ adjusted_input_len=$(( INPUT_LEN - prefix_len ))
    # start from request-rate as int(throughput) + 1
        request_rate=$((${throughput%.*} + 1))
        while ((request_rate > 0)); do
-            profile_index=$((profile_index+1))
            # clear prefix cache
            curl -X POST http://0.0.0.0:8004/reset_prefix_cache
            sleep 5
            bm_log="$LOG_FOLDER/bm_log_${max_num_seqs}_${max_num_batched_tokens}_requestrate_${request_rate}.txt"
-            python3 benchmarks/benchmark_serving.py \
+            vllm bench serve \
                --backend vllm \
                --model $MODEL  \
                --dataset-name random \
@ -193,12 +202,7 @@ adjusted_input_len=$(( INPUT_LEN - prefix_len ))
            best_max_num_seqs=$max_num_seqs
            best_num_batched_tokens=$max_num_batched_tokens
            best_goodput=$goodput
-            if [[ "$SYSTEM" == "TPU" ]]; then
-                update_best_profile "$profile_dir/plugins/profile" $profile_index
-            fi
-            if [[ "$SYSTEM" == "GPU" ]]; then
-                update_best_profile "$profile_dir" $profile_index
-            fi
+            best_request_rate=$request_rate
        fi
    else
        echo "max_num_seqs: $max_num_seqs, max_num_batched_tokens: $max_num_batched_tokens does not meet latency requirement ${MAX_LATENCY_ALLOWED_MS}"
@ -207,7 +211,7 @@ adjusted_input_len=$(( INPUT_LEN - prefix_len ))

    echo "best_max_num_seqs: $best_max_num_seqs, best_num_batched_tokens: $best_num_batched_tokens, best_throughput: $best_throughput"

-    pkill vllm
+    pkill -if vllm
    sleep 10
    printf '=%.0s' $(seq 1 20)
    return 0
@ -220,7 +224,8 @@ read -r -a num_batched_tokens_list <<< "$NUM_BATCHED_TOKENS_LIST"
 gpu_memory_utilization=0.98
 find_gpu_memory_utilization=0
 while (( $(echo "$gpu_memory_utilization >= 0.9" | bc -l) )); do
-    start_server $gpu_memory_utilization "${num_seqs_list[-1]}" "${num_batched_tokens_list[-1]}" "$LOG_FOLDER/vllm_log_gpu_memory_utilization_$gpu_memory_utilization.log"
+    # Pass empty string for profile_dir argument
+    start_server $gpu_memory_utilization "${num_seqs_list[-1]}" "${num_batched_tokens_list[-1]}" "$LOG_FOLDER/vllm_log_gpu_memory_utilization_$gpu_memory_utilization.log" ""
    result=$?
    if [[ "$result" -eq 0 ]]; then
        find_gpu_memory_utilization=1
@ -243,6 +248,45 @@ for num_seqs in "${num_seqs_list[@]}"; do
    done
 done
 echo "finish permutations"
+
+# =================================================================================
+# FINAL PROFILING RUN FOR THE BEST CONFIGURATION
+# =================================================================================
+if (( $(echo "$best_throughput > 0" | bc -l) )); then
+    echo
+    echo "Benchmark tuning finished. Now running profiling on the best configuration found..."
+    echo "Best config: max_num_seqs: $best_max_num_seqs, max_num_batched_tokens: $best_num_batched_tokens, throughput: $best_throughput"
+    echo
+
+    vllm_log="$LOG_FOLDER/vllm_log_BEST_PROFILE.txt"
+    bm_log="$LOG_FOLDER/bm_log_BEST_PROFILE.txt"
+
+    # Start server with the best params and profiling ENABLED
+    echo "Starting server for profiling..."
+    start_server $gpu_memory_utilization $best_max_num_seqs $best_num_batched_tokens "$vllm_log" "$PROFILE_PATH"
+
+    # Run benchmark with the best params and the --profile flag
+    echo "Running benchmark with profiling..."
+    prefix_len=$(( INPUT_LEN * MIN_CACHE_HIT_PCT / 100 ))
+    adjusted_input_len=$(( INPUT_LEN - prefix_len ))
+    vllm bench serve \
+        --backend vllm \
+        --model $MODEL \
+        --dataset-name random \
+        --random-input-len $adjusted_input_len \
+        --random-output-len $OUTPUT_LEN \
+        --ignore-eos \
+        --disable-tqdm \
+        --request-rate $best_request_rate \
+        --percentile-metrics ttft,tpot,itl,e2el \
+        --goodput e2el:$MAX_LATENCY_ALLOWED_MS \
+        --num-prompts 100 \
+        --random-prefix-len $prefix_len \
+        --port 8004 \
+        --profile &> "$bm_log"
+else
+    echo "No configuration met the latency requirements. Skipping final profiling run."
+fi
+pkill -if vllm
 echo "best_max_num_seqs: $best_max_num_seqs, best_num_batched_tokens: $best_num_batched_tokens, best_throughput: $best_throughput, profile saved in: $PROFILE_PATH"
 echo "best_max_num_seqs: $best_max_num_seqs, best_num_batched_tokens: $best_num_batched_tokens, best_throughput: $best_throughput, profile saved in: $PROFILE_PATH" >> "$RESULT"
-
--- a/benchmarks/backend_request_func.py
+++ b/benchmarks/backend_request_func.py
@ -31,9 +31,10 @@ class RequestFuncInput:
    model_name: Optional[str] = None
    logprobs: Optional[int] = None
    extra_body: Optional[dict] = None
-    multi_modal_content: Optional[dict] = None
+    multi_modal_content: Optional[dict | list[dict]] = None
    ignore_eos: bool = False
    language: Optional[str] = None
+    request_id: Optional[str] = None


@dataclass
@ -71,6 +72,9 @@ async def async_request_tgi(
            "inputs": request_func_input.prompt,
            "parameters": params,
        }
+        headers = None
+        if request_func_input.request_id:
+            headers = {"x-request-id": request_func_input.request_id}
        output = RequestFuncOutput()
        output.prompt_len = request_func_input.prompt_len
        if request_func_input.ignore_eos:
@ -82,7 +86,9 @@ async def async_request_tgi(
        st = time.perf_counter()
        most_recent_timestamp = st
        try:
-            async with session.post(url=api_url, json=payload) as response:
+            async with session.post(
+                url=api_url, json=payload, headers=headers
+            ) as response:
                if response.status == 200:
                    async for chunk_bytes in response.content:
                        chunk_bytes = chunk_bytes.strip()
@ -145,6 +151,9 @@ async def async_request_trt_llm(
        }
        if request_func_input.ignore_eos:
            payload["min_length"] = request_func_input.output_len
+        headers = None
+        if request_func_input.request_id:
+            headers = {"x-request-id": request_func_input.request_id}
        output = RequestFuncOutput()
        output.prompt_len = request_func_input.prompt_len

@ -152,7 +161,9 @@ async def async_request_trt_llm(
        st = time.perf_counter()
        most_recent_timestamp = st
        try:
-            async with session.post(url=api_url, json=payload) as response:
+            async with session.post(
+                url=api_url, json=payload, headers=headers
+            ) as response:
                if response.status == 200:
                    async for chunk_bytes in response.content:
                        chunk_bytes = chunk_bytes.strip()
@ -211,6 +222,8 @@ async def async_request_deepspeed_mii(
            "top_p": 1.0,
        }
        headers = {"Authorization": f"Bearer {os.environ.get('OPENAI_API_KEY')}"}
+        if request_func_input.request_id:
+            headers["x-request-id"] = request_func_input.request_id

        output = RequestFuncOutput()
        output.prompt_len = request_func_input.prompt_len
@ -283,6 +296,8 @@ async def async_request_openai_completions(
        if request_func_input.extra_body:
            payload.update(request_func_input.extra_body)
        headers = {"Authorization": f"Bearer {os.environ.get('OPENAI_API_KEY')}"}
+        if request_func_input.request_id:
+            headers["x-request-id"] = request_func_input.request_id

        output = RequestFuncOutput()
        output.prompt_len = request_func_input.prompt_len
@ -364,7 +379,15 @@ async def async_request_openai_chat_completions(
    ) as session:
        content = [{"type": "text", "text": request_func_input.prompt}]
        if request_func_input.multi_modal_content:
-            content.append(request_func_input.multi_modal_content)
+            mm_content = request_func_input.multi_modal_content
+            if isinstance(mm_content, list):
+                content.extend(mm_content)
+            elif isinstance(mm_content, dict):
+                content.append(mm_content)
+            else:
+                raise TypeError(
+                    "multi_modal_content must be a dict or list[dict] for openai-chat"
+                )
        payload = {
            "model": request_func_input.model_name
            if request_func_input.model_name
@ -387,6 +410,8 @@ async def async_request_openai_chat_completions(
            "Content-Type": "application/json",
            "Authorization": f"Bearer {os.environ.get('OPENAI_API_KEY')}",
        }
+        if request_func_input.request_id:
+            headers["x-request-id"] = request_func_input.request_id

        output = RequestFuncOutput()
        output.prompt_len = request_func_input.prompt_len
@ -483,6 +508,8 @@ async def async_request_openai_audio(
        headers = {
            "Authorization": f"Bearer {os.environ.get('OPENAI_API_KEY')}",
        }
+        if request_func_input.request_id:
+            headers["x-request-id"] = request_func_input.request_id

        # Send audio file
        def to_bytes(y, sr):
@ -491,7 +518,10 @@ async def async_request_openai_audio(
            buffer.seek(0)
            return buffer

-        with to_bytes(*request_func_input.multi_modal_content["audio"]) as f:
+        mm_audio = request_func_input.multi_modal_content
+        if not isinstance(mm_audio, dict) or "audio" not in mm_audio:
+            raise TypeError("multi_modal_content must be a dict containing 'audio'")
+        with to_bytes(*mm_audio["audio"]) as f:
            form = aiohttp.FormData()
            form.add_field("file", f, content_type="audio/wav")
            for key, value in payload.items():
--- a/benchmarks/benchmark_block_pool.py
+++ b/benchmarks/benchmark_block_pool.py
@ -0,0 +1,74 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+import gc
+
+from tabulate import tabulate
+
+from benchmark_utils import TimeCollector
+from vllm.utils import FlexibleArgumentParser
+from vllm.v1.core.block_pool import BlockPool
+
+
+def main(args):
+    rows = []
+    for allocate_block in args.allocate_blocks:
+        # Enforce a GC collect ahead to minimize the impact among runs
+        gc.collect()
+        block_pool = BlockPool(num_gpu_blocks=args.num_gpu_blocks, enable_caching=True)
+
+        get_blocks_times = TimeCollector(TimeCollector.US)
+        free_blocks_times = TimeCollector(TimeCollector.US)
+        for _ in range(args.num_iteration):
+            with get_blocks_times:
+                blocks = block_pool.get_new_blocks(allocate_block)
+            with free_blocks_times:
+                block_pool.free_blocks(blocks)
+
+        rows.append(
+            [get_blocks_times.cnt, args.num_gpu_blocks, allocate_block]
+            + get_blocks_times.dump_avg_max()
+            + free_blocks_times.dump_avg_max()
+        )
+
+    print(
+        tabulate(
+            rows,
+            headers=[
+                "Iterations",
+                "Total\nBlocks",
+                "Allocated\nBlocks",
+                "Get Blocks\nAvg (us)",
+                "Get Blocks\nMax (us)",
+                "Free Blocks\nAvg (us)",
+                "Free Blocks\nMax (us)",
+            ],
+            tablefmt="grid",
+            floatfmt=".3f",
+        )
+    )
+
+
+def invoke_main() -> None:
+    parser = FlexibleArgumentParser(
+        description="Benchmark the performance of BlockPool for KV Cache."
+    )
+    parser.add_argument("--num-gpu-blocks", type=int, default=100000)
+    parser.add_argument(
+        "--num-iteration",
+        type=int,
+        default=1000,
+        help="Number of iterations to run to stablize final data readings",
+    )
+    parser.add_argument(
+        "--allocate-blocks",
+        type=int,
+        nargs="*",
+        default=[10, 50, 100, 500, 1000],
+        help="Number of blocks to allocate",
+    )
+    args = parser.parse_args()
+    main(args)
+
+
+if __name__ == "__main__":
+    invoke_main()  # pragma: no cover
--- a/benchmarks/benchmark_dataset.py
+++ b/benchmarks/benchmark_dataset.py
@ -19,6 +19,7 @@ import logging
 import random
 from abc import ABC, abstractmethod
 from collections.abc import Mapping
+from copy import deepcopy
 from dataclasses import dataclass
 from functools import cache
 from io import BytesIO
@ -52,8 +53,9 @@ class SampleRequest:
    prompt: Union[str, Any]
    prompt_len: int
    expected_output_len: int
-    multi_modal_data: Optional[Union[MultiModalDataDict, dict]] = None
+    multi_modal_data: Optional[Union[MultiModalDataDict, dict, list[dict]]] = None
    lora_request: Optional[LoRARequest] = None
+    request_id: Optional[str] = None


 # -----------------------------------------------------------------------------
@ -155,7 +157,10 @@ class BenchmarkDataset(ABC):

    @abstractmethod
    def sample(
-        self, tokenizer: PreTrainedTokenizerBase, num_requests: int
+        self,
+        tokenizer: PreTrainedTokenizerBase,
+        num_requests: int,
+        request_id_prefix: str = "",
    ) -> list[SampleRequest]:
        """
        Abstract method to generate sample requests from the dataset.
@ -167,6 +172,7 @@ class BenchmarkDataset(ABC):
            tokenizer (PreTrainedTokenizerBase): The tokenizer to be used
             for processing the dataset's text.
            num_requests (int): The number of sample requests to generate.
+            request_id_prefix (str) The prefix of request_id.

        Returns:
            list[SampleRequest]: A list of sample requests generated from the
@ -175,7 +181,10 @@ class BenchmarkDataset(ABC):
        raise NotImplementedError("sample must be implemented in subclasses.")

    def maybe_oversample_requests(
-        self, requests: list[SampleRequest], num_requests: int
+        self,
+        requests: list[SampleRequest],
+        num_requests: int,
+        request_id_prefix: str = "",
    ) -> None:
        """
        Oversamples the list of requests if its size is less than the desired
@ -183,11 +192,18 @@ class BenchmarkDataset(ABC):

        Args:
            requests (List[SampleRequest]): The current list of sampled
-            requests.  num_requests (int): The target number of requests.
+            requests.
+            num_requests (int): The target number of requests.
+            request_id_prefix (str) The prefix of the request ids.
        """
        if len(requests) < num_requests:
            random.seed(self.random_seed)
-            additional = random.choices(requests, k=num_requests - len(requests))
+            additional = deepcopy(
+                random.choices(requests, k=num_requests - len(requests))
+            )
+            for i in range(len(additional)):
+                req = additional[i]
+                req.request_id = request_id_prefix + str(len(requests) + i)
            requests.extend(additional)
            logger.info("Oversampled requests to reach %d total samples.", num_requests)

@ -277,6 +293,41 @@ def process_image(image: Any) -> Mapping[str, Any]:
    )


+def process_video(video: Any) -> Mapping[str, Any]:
+    """
+    Process a single video input and return a multimedia content dictionary.
+
+    Supports the following input types:
+
+    1. Dictionary with raw video bytes: - Expects a dict with a 'bytes' key
+       containing raw video data.
+
+    2. String input: - Treats the string as a URL or local file path.  -
+       Prepends "file://" if the string doesn't start with "http://" or
+       "file://".  - Returns a dictionary with the image URL.
+
+    Raises:
+        ValueError: If the input is not a supported type.
+    """
+    if isinstance(video, dict) and "bytes" in video:
+        video_bytes = video["bytes"]
+        video_base64 = base64.b64encode(video_bytes).decode("utf-8")
+        return {
+            "type": "video_url",
+            "video_url": {"url": f"data:video/mp4;base64,{video_base64}"},
+        }
+
+    if isinstance(video, str):
+        video_url = (
+            video if video.startswith(("http://", "file://")) else f"file://{video}"
+        )
+        return {"type": "video_url", "video_url": {"url": video_url}}
+
+    raise ValueError(
+        f"Invalid video input {video}. Must be a string of local path/remote url, or a dictionary with raw video bytes in the form of `{{'bytes': raw_video_bytes}}`."  # noqa: E501
+    )
+
+
 # -----------------------------------------------------------------------------
 # Random Dataset Implementation (Synthetic Data)
 # -----------------------------------------------------------------------------
@ -303,6 +354,7 @@ class RandomDataset(BenchmarkDataset):
        range_ratio: float = DEFAULT_RANGE_RATIO,
        input_len: int = DEFAULT_INPUT_LEN,
        output_len: int = DEFAULT_OUTPUT_LEN,
+        request_id_prefix: str = "",
        **kwargs,
    ) -> list[SampleRequest]:
        # Enforce range_ratio < 1
@ -363,8 +415,10 @@ class RandomDataset(BenchmarkDataset):
                    prompt=prompt,
                    prompt_len=total_input_len,
                    expected_output_len=int(output_lens[i]),
+                    request_id=request_id_prefix + str(i),
                )
            )
+
        return requests


@ -406,9 +460,11 @@ class ShareGPTDataset(BenchmarkDataset):
        max_loras: Optional[int] = None,
        output_len: Optional[int] = None,
        enable_multimodal_chat: bool = False,
+        request_id_prefix: str = "",
        **kwargs,
    ) -> list:
        samples: list = []
+        ind = 0
        for entry in self.data:
            if len(samples) >= num_requests:
                break
@ -430,17 +486,26 @@ class ShareGPTDataset(BenchmarkDataset):
                skip_min_output_len_check=output_len is not None,
            ):
                continue
+            if image_path := entry.get("image"):
+                mm_content = process_image(image_path)
+            elif video_path := entry.get("video"):
+                mm_content = process_video(video_path)
+            else:
+                mm_content = None
            if enable_multimodal_chat:
-                prompt = self.apply_multimodal_chat_transformation(prompt, None)
+                prompt = self.apply_multimodal_chat_transformation(prompt, mm_content)
            samples.append(
                SampleRequest(
                    prompt=prompt,
                    prompt_len=prompt_len,
                    expected_output_len=new_output_len,
                    lora_request=lora_request,
+                    multi_modal_data=mm_content,
+                    request_id=request_id_prefix + str(ind),
                )
            )
-        self.maybe_oversample_requests(samples, num_requests)
+            ind += 1
+        self.maybe_oversample_requests(samples, num_requests, request_id_prefix)
        return samples


@ -506,10 +571,11 @@ class CustomDataset(BenchmarkDataset):
        output_len: Optional[int] = None,
        enable_multimodal_chat: bool = False,
        skip_chat_template: bool = False,
+        request_id_prefix: str = "",
        **kwargs,
    ) -> list:
        sampled_requests = []
-        for item in self.data:
+        for i, item in enumerate(self.data):
            if len(sampled_requests) >= num_requests:
                break
            prompt = item["prompt"]
@ -528,9 +594,12 @@ class CustomDataset(BenchmarkDataset):
                    prompt=prompt,
                    prompt_len=prompt_len,
                    expected_output_len=output_len,
+                    request_id=request_id_prefix + str(i),
                )
            )
-        self.maybe_oversample_requests(sampled_requests, num_requests)
+        self.maybe_oversample_requests(
+            sampled_requests, num_requests, request_id_prefix
+        )

        return sampled_requests

@ -572,6 +641,7 @@ class SonnetDataset(BenchmarkDataset):
        input_len: int = DEFAULT_INPUT_LEN,
        output_len: int = DEFAULT_OUTPUT_LEN,
        return_prompt_formatted: bool = False,
+        request_id_prefix: str = "",
        **kwargs,
    ) -> list:
        # Calculate average token length for a poem line.
@ -597,6 +667,7 @@ class SonnetDataset(BenchmarkDataset):
        prefix_lines = self.data[:num_prefix_lines]

        samples = []
+        ind = 0
        while len(samples) < num_requests:
            extra_lines = random.choices(
                self.data, k=num_input_lines - num_prefix_lines
@ -607,14 +678,17 @@ class SonnetDataset(BenchmarkDataset):
                msg, add_generation_prompt=True, tokenize=False
            )
            prompt_len = len(tokenizer(prompt_formatted).input_ids)
+
            if prompt_len <= input_len:
                samples.append(
                    SampleRequest(
                        prompt=prompt_formatted if return_prompt_formatted else prompt,
                        prompt_len=prompt_len,
                        expected_output_len=output_len,
+                        request_id=request_id_prefix + str(ind),
                    )
                )
+                ind += 1
        return samples


@ -666,6 +740,7 @@ class BurstGPTDataset(BenchmarkDataset):
        num_requests: int,
        max_loras: Optional[int] = None,
        lora_path: Optional[str] = None,
+        request_id_prefix: str = "",
        **kwargs,
    ) -> list[SampleRequest]:
        samples = []
@ -687,6 +762,7 @@ class BurstGPTDataset(BenchmarkDataset):
                    prompt_len=input_len,
                    expected_output_len=output_len,
                    lora_request=lora_req,
+                    request_id=request_id_prefix + str(i),
                )
            )
        return samples
@ -746,12 +822,14 @@ class ConversationDataset(HuggingFaceDataset):
        num_requests: int,
        output_len: Optional[int] = None,
        enable_multimodal_chat: bool = False,
+        request_id_prefix: str = "",
        **kwargs,
    ) -> list:
        # Filter examples with at least 2 conversations
        filtered_data = self.data.filter(lambda x: len(x["conversations"]) >= 2)
        sampled_requests = []
        dynamic_output = output_len is None
+        ind = 0

        for item in filtered_data:
            if len(sampled_requests) >= num_requests:
@ -779,9 +857,13 @@ class ConversationDataset(HuggingFaceDataset):
                    prompt_len=prompt_len,
                    expected_output_len=output_len,
                    multi_modal_data=mm_content,
+                    request_id=request_id_prefix + str(ind),
                )
            )
-        self.maybe_oversample_requests(sampled_requests, num_requests)
+            ind += 1
+        self.maybe_oversample_requests(
+            sampled_requests, num_requests, request_id_prefix
+        )
        return sampled_requests


@ -808,11 +890,12 @@ class VisionArenaDataset(HuggingFaceDataset):
        num_requests: int,
        output_len: Optional[int] = None,
        enable_multimodal_chat: bool = False,
+        request_id_prefix: str = "",
        **kwargs,
    ) -> list:
        output_len = output_len if output_len is not None else self.DEFAULT_OUTPUT_LEN
        sampled_requests = []
-        for item in self.data:
+        for i, item in enumerate(self.data):
            if len(sampled_requests) >= num_requests:
                break
            parser_fn = self.SUPPORTED_DATASET_PATHS.get(self.dataset_path)
@ -832,9 +915,12 @@ class VisionArenaDataset(HuggingFaceDataset):
                    prompt_len=prompt_len,
                    expected_output_len=output_len,
                    multi_modal_data=mm_content,
+                    request_id=request_id_prefix + str(i),
                )
            )
-        self.maybe_oversample_requests(sampled_requests, num_requests)
+        self.maybe_oversample_requests(
+            sampled_requests, num_requests, request_id_prefix
+        )
        return sampled_requests


@ -864,15 +950,18 @@ class InstructCoderDataset(HuggingFaceDataset):
        num_requests: int,
        output_len: Optional[int] = None,
        enable_multimodal_chat: bool = False,
+        request_id_prefix: str = "",
        **kwargs,
    ) -> list:
        output_len = output_len if output_len is not None else self.DEFAULT_OUTPUT_LEN
        sampled_requests = []
-        for item in self.data:
+        for i, item in enumerate(self.data):
            if len(sampled_requests) >= num_requests:
                break
-            prompt = f"{item['input']}\n\n{item['instruction']} Just output \
-            the code, do not include any explanation."
+            prompt = (
+                f"{item['input']}\n\n{item['instruction']} Just output "
+                "the code, do not include any explanation."
+            )

            # apply template
            prompt = tokenizer.apply_chat_template(
@ -886,9 +975,12 @@ class InstructCoderDataset(HuggingFaceDataset):
                    prompt=prompt,
                    prompt_len=prompt_len,
                    expected_output_len=output_len,
+                    request_id=request_id_prefix + str(i),
                )
            )
-        self.maybe_oversample_requests(sampled_requests, num_requests)
+        self.maybe_oversample_requests(
+            sampled_requests, num_requests, request_id_prefix
+        )
        return sampled_requests


@ -918,12 +1010,13 @@ class MTBenchDataset(HuggingFaceDataset):
        num_requests: int,
        output_len: Optional[int] = None,
        enable_multimodal_chat: bool = False,
+        request_id_prefix: str = "",
        **kwargs,
    ) -> list:
        output_len = output_len if output_len is not None else self.DEFAULT_OUTPUT_LEN
        sampled_requests = []

-        for item in self.data:
+        for i, item in enumerate(self.data):
            if len(sampled_requests) >= num_requests:
                break
            prompt = item["turns"][0]
@ -941,9 +1034,12 @@ class MTBenchDataset(HuggingFaceDataset):
                    prompt=prompt,
                    prompt_len=prompt_len,
                    expected_output_len=output_len,
+                    request_id=request_id_prefix + str(i),
                )
            )
-        self.maybe_oversample_requests(sampled_requests, num_requests)
+        self.maybe_oversample_requests(
+            sampled_requests, num_requests, request_id_prefix
+        )
        return sampled_requests


@ -968,10 +1064,12 @@ class AIMODataset(HuggingFaceDataset):
        tokenizer: PreTrainedTokenizerBase,
        num_requests: int,
        output_len: Optional[int] = None,
+        request_id_prefix: str = "",
        **kwargs,
    ) -> list:
        sampled_requests = []
        dynamic_output = output_len is None
+        ind = 0

        for item in self.data:
            if len(sampled_requests) >= num_requests:
@ -994,9 +1092,13 @@ class AIMODataset(HuggingFaceDataset):
                    prompt_len=prompt_len,
                    expected_output_len=output_len,
                    multi_modal_data=None,
+                    request_id=request_id_prefix + str(ind),
                )
            )
-        self.maybe_oversample_requests(sampled_requests, num_requests)
+            ind += 1
+        self.maybe_oversample_requests(
+            sampled_requests, num_requests, request_id_prefix
+        )
        return sampled_requests


@ -1066,12 +1168,18 @@ class NextEditPredictionDataset(HuggingFaceDataset):
        "zed-industries/zeta": _format_zeta_prompt,
    }

-    def sample(self, tokenizer: PreTrainedTokenizerBase, num_requests: int, **kwargs):
+    def sample(
+        self,
+        tokenizer: PreTrainedTokenizerBase,
+        num_requests: int,
+        request_id_prefix: str = "",
+        **kwargs,
+    ):
        formatting_prompt_func = self.MAPPING_PROMPT_FUNCS.get(self.dataset_path)
        if formatting_prompt_func is None:
            raise ValueError(f"Unsupported dataset path: {self.dataset_path}")
        samples = []
-        for sample in self.data:
+        for i, sample in enumerate(self.data):
            sample = formatting_prompt_func(sample)
            samples.append(
                SampleRequest(
@ -1080,11 +1188,12 @@ class NextEditPredictionDataset(HuggingFaceDataset):
                    expected_output_len=len(
                        tokenizer(sample["expected_output"]).input_ids
                    ),
+                    request_id=request_id_prefix + str(i),
                )
            )
            if len(samples) >= num_requests:
                break
-        self.maybe_oversample_requests(samples, num_requests)
+        self.maybe_oversample_requests(samples, num_requests, request_id_prefix)
        return samples


@ -1133,6 +1242,7 @@ class ASRDataset(HuggingFaceDataset):
        tokenizer: PreTrainedTokenizerBase,
        num_requests: int,
        output_len: Optional[int] = None,
+        request_id_prefix: str = "",
        **kwargs,
    ) -> list:
        import librosa
@ -1142,6 +1252,7 @@ class ASRDataset(HuggingFaceDataset):
        prompt_len = len(tokenizer(prompt).input_ids)
        sampled_requests = []
        skipped = 0
+        ind = 0
        for item in self.data:
            if len(sampled_requests) >= num_requests:
                break
@ -1160,8 +1271,10 @@ class ASRDataset(HuggingFaceDataset):
                    prompt_len=prompt_len,
                    expected_output_len=output_len,
                    multi_modal_data=mm_content,
+                    request_id=request_id_prefix + str(ind),
                )
            )
+            ind += 1
        if skipped:
            logger.warning(
                "%d samples discarded from dataset due to"
@ -1169,5 +1282,7 @@ class ASRDataset(HuggingFaceDataset):
                " what Whisper supports.",
                skipped,
            )
-        self.maybe_oversample_requests(sampled_requests, num_requests)
+        self.maybe_oversample_requests(
+            sampled_requests, num_requests, request_id_prefix
+        )
        return sampled_requests
--- a/benchmarks/benchmark_latency.py
+++ b/benchmarks/benchmark_latency.py
@ -11,6 +11,7 @@ from typing import Any, Optional

 import numpy as np
 from tqdm import tqdm
+from typing_extensions import deprecated

 import vllm.envs as envs
 from benchmark_utils import convert_to_pytorch_benchmark_format, write_to_json
@ -34,6 +35,10 @@ def save_to_pytorch_benchmark_format(
        write_to_json(pt_file, pt_records)


+@deprecated(
+    "benchmark_latency.py is deprecated and will be removed in a "
+    "future version. Please use 'vllm bench latency' instead.",
+)
 def main(args: argparse.Namespace):
    print(args)

--- a/benchmarks/benchmark_ngram_proposer.py
+++ b/benchmarks/benchmark_ngram_proposer.py
@ -0,0 +1,112 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+import gc
+
+import numpy as np
+from tabulate import tabulate
+
+from benchmark_utils import TimeCollector
+from vllm.config import ModelConfig, SpeculativeConfig, VllmConfig
+from vllm.utils import FlexibleArgumentParser
+from vllm.v1.spec_decode.ngram_proposer import NgramProposer
+
+
+def main(args):
+    rows = []
+    for max_ngram in args.max_ngram:
+        collector = TimeCollector(TimeCollector.US)
+
+        model_config = ModelConfig(
+            model="facebook/opt-125m",
+            task="generate",
+            max_model_len=args.num_token + args.num_spec_token,
+            tokenizer="facebook/opt-125m",
+            tokenizer_mode="auto",
+            dtype="auto",
+            seed=None,
+            trust_remote_code=False,
+        )
+        proposer = NgramProposer(
+            vllm_config=VllmConfig(
+                model_config=model_config,
+                speculative_config=SpeculativeConfig(
+                    prompt_lookup_min=args.min_ngram,
+                    prompt_lookup_max=max_ngram,
+                    num_speculative_tokens=args.num_spec_token,
+                    method="ngram",
+                ),
+            )
+        )
+
+        # Warm up
+        proposer.propose(np.random.randint(0, 20, (args.num_token,)))
+
+        gc.collect()
+        for _ in range(args.num_iteration):
+            tokens = np.random.randint(0, 20, (args.num_req, args.num_token))
+            with collector:
+                for i in range(args.num_req):
+                    proposer.propose(tokens[i, :])
+        rows.append(
+            [args.num_req, args.num_token, args.min_ngram, max_ngram]
+            + collector.dump_avg_max()
+        )
+
+    print(
+        tabulate(
+            rows,
+            headers=[
+                "# Request",
+                "# Token",
+                "Min Ngram",
+                "Max Ngram",
+                "Avg (us)",
+                "Max (us)",
+            ],
+            tablefmt="grid",
+            floatfmt=".3f",
+        )
+    )
+
+
+def invoke_main() -> None:
+    parser = FlexibleArgumentParser(
+        description="Benchmark the performance of N-gram speculative decode drafting"
+    )
+    parser.add_argument(
+        "--num-iteration",
+        type=int,
+        default=100,
+        help="Number of iterations to run to stablize final data readings",
+    )
+    parser.add_argument(
+        "--num-req", type=int, default=128, help="Number of requests in the batch"
+    )
+    parser.add_argument(
+        "--num-token", type=int, default=1500, help="Number of tokens for each request"
+    )
+    parser.add_argument(
+        "--min-ngram",
+        type=int,
+        default=3,
+        help="Minimum n-gram to match",
+    )
+    parser.add_argument(
+        "--max-ngram",
+        type=int,
+        nargs="*",
+        default=[5, 7, 10, 15, 20],
+        help="Maximum n-gram to match",
+    )
+    parser.add_argument(
+        "--num-spec-token",
+        type=int,
+        default=3,
+        help="Number of speculative tokens to generate",
+    )
+    args = parser.parse_args()
+    main(args)
+
+
+if __name__ == "__main__":
+    invoke_main()  # pragma: no cover
--- a/benchmarks/benchmark_serving.py
+++ b/benchmarks/benchmark_serving.py
@ -5,8 +5,7 @@ r"""Benchmark online serving throughput.
 On the server side, run one of the following commands:
    vLLM OpenAI API server
    vllm serve <your_model> \
-        --swap-space 16 \
-        --disable-log-requests
+        --swap-space 16

 On the client side, run:
    python benchmarks/benchmark_serving.py \
@ -38,6 +37,7 @@ from typing import Any, Literal, Optional
 import numpy as np
 from tqdm.asyncio import tqdm
 from transformers import PreTrainedTokenizerBase
+from typing_extensions import deprecated

 from backend_request_func import (
    ASYNC_REQUEST_FUNCS,
@ -263,7 +263,14 @@ async def benchmark(
        input_requests[0].multi_modal_data,
    )

-    assert test_mm_content is None or isinstance(test_mm_content, dict)
+    assert (
+        test_mm_content is None
+        or isinstance(test_mm_content, dict)
+        or (
+            isinstance(test_mm_content, list)
+            and all(isinstance(item, dict) for item in test_mm_content)
+        )
+    ), "multi_modal_data must be a dict or list[dict]"
    test_input = RequestFuncInput(
        model=model_id,
        model_name=model_name,
@ -368,11 +375,12 @@ async def benchmark(
                    rps_change_events.append({"rps": rps_val, "timestamp": timestamp})
                last_int_rps = current_int_rps

-        prompt, prompt_len, output_len, mm_content = (
+        prompt, prompt_len, output_len, mm_content, request_id = (
            request.prompt,
            request.prompt_len,
            request.expected_output_len,
            request.multi_modal_data,
+            request.request_id,
        )
        req_model_id, req_model_name = model_id, model_name
        if lora_modules:
@ -390,25 +398,12 @@ async def benchmark(
            multi_modal_content=mm_content,
            ignore_eos=ignore_eos,
            extra_body=extra_body,
+            request_id=request_id,
        )
        task = limited_request_func(request_func_input=request_func_input, pbar=pbar)
        tasks.append(asyncio.create_task(task))
    outputs: list[RequestFuncOutput] = await asyncio.gather(*tasks)

-    if profile:
-        print("Stopping profiler...")
-        profile_input = RequestFuncInput(
-            model=model_id,
-            prompt=test_prompt,
-            api_url=base_url + "/stop_profile",
-            prompt_len=test_prompt_len,
-            output_len=test_output_len,
-            logprobs=logprobs,
-        )
-        profile_output = await request_func(request_func_input=profile_input)
-        if profile_output.success:
-            print("Profiler stopped")
-
    if pbar is not None:
        pbar.close()

@ -426,6 +421,10 @@ async def benchmark(

    print("{s:{c}^{n}}".format(s=" Serving Benchmark Result ", n=50, c="="))
    print("{:<40} {:<10}".format("Successful requests:", metrics.completed))
+    if max_concurrency is not None:
+        print("{:<40} {:<10}".format("Maximum request concurrency:", max_concurrency))
+    if request_rate != float("inf"):
+        print("{:<40} {:<10.2f}".format("Request rate configured (RPS):", request_rate))
    print("{:<40} {:<10.2f}".format("Benchmark duration (s):", benchmark_duration))
    print("{:<40} {:<10}".format("Total input tokens:", metrics.total_input))
    print("{:<40} {:<10}".format("Total generated tokens:", metrics.total_output))
@ -517,6 +516,20 @@ async def benchmark(

    print("=" * 50)

+    if profile:
+        print("Stopping profiler...")
+        profile_input = RequestFuncInput(
+            model=model_id,
+            prompt=test_prompt,
+            api_url=base_url + "/stop_profile",
+            prompt_len=test_prompt_len,
+            output_len=test_output_len,
+            logprobs=logprobs,
+        )
+        profile_output = await request_func(request_func_input=profile_input)
+        if profile_output.success:
+            print("Profiler stopped")
+
    return result


@ -593,6 +606,10 @@ def save_to_pytorch_benchmark_format(
        write_to_json(pt_file, pt_records)


+@deprecated(
+    "benchmark_serving.py is deprecated and will be removed in a future "
+    "version. Please use 'vllm bench serve' instead.",
+)
 def main(args: argparse.Namespace):
    print(args)
    random.seed(args.seed)
@ -650,6 +667,7 @@ def main(args: argparse.Namespace):
            tokenizer=tokenizer,
            output_len=args.custom_output_len,
            skip_chat_template=args.custom_skip_chat_template,
+            request_id_prefix=args.request_id_prefix,
        )

    elif args.dataset_name == "sonnet":
@ -663,6 +681,7 @@ def main(args: argparse.Namespace):
                prefix_len=args.sonnet_prefix_len,
                tokenizer=tokenizer,
                return_prompt_formatted=False,
+                request_id_prefix=args.request_id_prefix,
            )
        else:
            assert tokenizer.chat_template or tokenizer.default_chat_template, (
@ -675,6 +694,7 @@ def main(args: argparse.Namespace):
                prefix_len=args.sonnet_prefix_len,
                tokenizer=tokenizer,
                return_prompt_formatted=True,
+                request_id_prefix=args.request_id_prefix,
            )

    elif args.dataset_name == "hf":
@ -736,6 +756,7 @@ def main(args: argparse.Namespace):
            num_requests=args.num_prompts,
            tokenizer=tokenizer,
            output_len=args.hf_output_len,
+            request_id_prefix=args.request_id_prefix,
        )

    else:
@ -747,10 +768,15 @@ def main(args: argparse.Namespace):
                tokenizer=tokenizer,
                num_requests=args.num_prompts,
                output_len=args.sharegpt_output_len,
+                request_id_prefix=args.request_id_prefix,
            ),
            "burstgpt": lambda: BurstGPTDataset(
                random_seed=args.seed, dataset_path=args.dataset_path
-            ).sample(tokenizer=tokenizer, num_requests=args.num_prompts),
+            ).sample(
+                tokenizer=tokenizer,
+                num_requests=args.num_prompts,
+                request_id_prefix=args.request_id_prefix,
+            ),
            "random": lambda: RandomDataset(dataset_path=args.dataset_path).sample(
                tokenizer=tokenizer,
                num_requests=args.num_prompts,
@ -758,6 +784,7 @@ def main(args: argparse.Namespace):
                input_len=args.random_input_len,
                output_len=args.random_output_len,
                range_ratio=args.random_range_ratio,
+                request_id_prefix=args.request_id_prefix,
            ),
        }

@ -1103,6 +1130,13 @@ def create_argument_parser():
        "goodput, refer to DistServe paper: https://arxiv.org/pdf/2401.09670 "
        "and the blog: https://hao-ai-lab.github.io/blogs/distserve",
    )
+    parser.add_argument(
+        "--request-id-prefix",
+        type=str,
+        required=False,
+        default="benchmark-serving",
+        help="Specify the prefix of request id.",
+    )

    # group for dataset specific arguments
    custom_group = parser.add_argument_group("custom dataset options")
--- a/benchmarks/benchmark_serving_structured_output.py
+++ b/benchmarks/benchmark_serving_structured_output.py
@ -4,7 +4,7 @@ r"""Benchmark online serving throughput with structured outputs.

 On the server side, run one of the following commands:
    (vLLM OpenAI API server)
-    vllm serve <your_model> --disable-log-requests
+    vllm serve <your_model>

 On the client side, run:
    python benchmarks/benchmark_serving_structured_output.py \
@ -538,20 +538,6 @@ async def benchmark(
        )
    outputs: list[RequestFuncOutput] = await asyncio.gather(*tasks)

-    if profile:
-        print("Stopping profiler...")
-        profile_input = RequestFuncInput(
-            model=model_id,
-            prompt=test_request.prompt,
-            api_url=base_url + "/stop_profile",
-            prompt_len=test_request.prompt_len,
-            output_len=test_request.expected_output_len,
-            extra_body={test_request.structure_type: test_request.schema},
-        )
-        profile_output = await request_func(request_func_input=profile_input)
-        if profile_output.success:
-            print("Profiler stopped")
-
    if pbar is not None:
        pbar.close()

@ -569,6 +555,10 @@ async def benchmark(

    print("{s:{c}^{n}}".format(s=" Serving Benchmark Result ", n=50, c="="))
    print("{:<40} {:<10}".format("Successful requests:", metrics.completed))
+    if max_concurrency is not None:
+        print("{:<40} {:<10}".format("Maximum request concurrency:", max_concurrency))
+    if request_rate != float("inf"):
+        print("{:<40} {:<10.2f}".format("Request rate configured (RPS):", request_rate))
    print("{:<40} {:<10.2f}".format("Benchmark duration (s):", benchmark_duration))
    print("{:<40} {:<10}".format("Total input tokens:", metrics.total_input))
    print("{:<40} {:<10}".format("Total generated tokens:", metrics.total_output))
@ -666,6 +656,20 @@ async def benchmark(

    print("=" * 50)

+    if profile:
+        print("Stopping profiler...")
+        profile_input = RequestFuncInput(
+            model=model_id,
+            prompt=test_request.prompt,
+            api_url=base_url + "/stop_profile",
+            prompt_len=test_request.prompt_len,
+            output_len=test_request.expected_output_len,
+            extra_body={test_request.structure_type: test_request.schema},
+        )
+        profile_output = await request_func(request_func_input=profile_input)
+        if profile_output.success:
+            print("Profiler stopped")
+
    return result, ret


--- a/benchmarks/benchmark_throughput.py
+++ b/benchmarks/benchmark_throughput.py
@ -15,6 +15,7 @@ import torch
 import uvloop
 from tqdm import tqdm
 from transformers import AutoModelForCausalLM, AutoTokenizer, PreTrainedTokenizerBase
+from typing_extensions import deprecated

 from benchmark_dataset import (
    AIMODataset,
@ -167,7 +168,8 @@ async def run_vllm_async(
    from vllm import SamplingParams

    async with build_async_engine_client_from_engine_args(
-        engine_args, disable_frontend_multiprocessing
+        engine_args,
+        disable_frontend_multiprocessing=disable_frontend_multiprocessing,
    ) as llm:
        model_config = await llm.get_model_config()
        assert all(
@ -381,6 +383,10 @@ def get_requests(args, tokenizer):
    return dataset_cls(**common_kwargs).sample(**sample_kwargs)


+@deprecated(
+    "benchmark_throughput.py is deprecated and will be removed in a "
+    "future version. Please use 'vllm bench throughput' instead.",
+)
 def main(args: argparse.Namespace):
    if args.seed is None:
        args.seed = 0
@ -591,8 +597,8 @@ def validate_args(args):
    # https://github.com/vllm-project/vllm/issues/16222
    if args.data_parallel_size > 1:
        raise ValueError(
-            "Data parallel is not supported in offline benchmark, \
-            please use benchmark serving instead"
+            "Data parallel is not supported in offline benchmark, "
+            "please use benchmark serving instead"
        )


--- a/benchmarks/benchmark_utils.py
+++ b/benchmarks/benchmark_utils.py
@ -1,11 +1,12 @@
 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-
 import argparse
 import json
 import math
 import os
-from typing import Any
+import time
+from types import TracebackType
+from typing import Any, Optional, Union


 def convert_to_pytorch_benchmark_format(
@ -72,3 +73,53 @@ def write_to_json(filename: str, records: list) -> None:
            cls=InfEncoder,
            default=lambda o: f"<{type(o).__name__} object is not JSON serializable>",
        )
+
+
+# Collect time and generate time metrics
+#
+# Example Usage:
+#   collector = TimeCollector(TimeCollector.US)
+#   for _ in range(total_iteration):
+#      with collector:
+#          ...
+#   collector.dump_avg_max()
+class TimeCollector:
+    NS: int = 1
+    US: int = NS * 1000
+    MS: int = US * 1000
+    S: int = MS * 1000
+
+    def __init__(self, scale: int) -> None:
+        self.cnt: int = 0
+        self._sum: int = 0
+        self._max: Optional[int] = None
+        self.scale = scale
+        self.start_time: int = time.monotonic_ns()
+
+    def collect(self, v: int) -> None:
+        self.cnt += 1
+        self._sum += v
+        if self._max is None:
+            self._max = v
+        else:
+            self._max = max(self._max, v)
+
+    def avg(self) -> Union[float, str]:
+        return self._sum * 1.0 / self.cnt / self.scale if self.cnt > 0 else "N/A"
+
+    def max(self) -> Union[float, str]:
+        return self._max / self.scale if self._max else "N/A"
+
+    def dump_avg_max(self) -> list[Union[float, str]]:
+        return [self.avg(), self.max()]
+
+    def __enter__(self) -> None:
+        self.start_time = time.monotonic_ns()
+
+    def __exit__(
+        self,
+        exc_type: Optional[type[BaseException]],
+        exc_value: Optional[BaseException],
+        exc_traceback: Optional[TracebackType],
+    ) -> None:
+        self.collect(time.monotonic_ns() - self.start_time)
--- a/benchmarks/disagg_benchmarks/disagg_overhead_benchmark.sh
+++ b/benchmarks/disagg_benchmarks/disagg_overhead_benchmark.sh
@ -3,7 +3,7 @@
 # benchmark the overhead of disaggregated prefill.
 # methodology:
 # - send all request to prefill vLLM instance. It will buffer KV cache.
-# - then send all request to decode instance. 
+# - then send all request to decode instance.
 # - The TTFT of decode instance is the overhead.

 set -ex
@ -12,6 +12,8 @@ kill_gpu_processes() {
  # kill all processes on GPU.
  pgrep pt_main_thread | xargs -r kill -9
  pgrep python3 | xargs -r kill -9
+  # vLLM now names the process with VLLM prefix after https://github.com/vllm-project/vllm/pull/21445
+  pgrep VLLM | xargs -r kill -9
  sleep 10

  # remove vllm config file
@ -61,7 +63,7 @@ benchmark() {
    --gpu-memory-utilization 0.6 \
    --kv-transfer-config \
    '{"kv_connector":"PyNcclConnector","kv_role":"kv_producer","kv_rank":0,"kv_parallel_size":2,"kv_buffer_size":5e9}' &
-    
+

  CUDA_VISIBLE_DEVICES=1 python3 \
    -m vllm.entrypoints.openai.api_server \
@ -76,38 +78,38 @@ benchmark() {
  wait_for_server 8200

  # let the prefill instance finish prefill
-  python3 ../benchmark_serving.py \
-          --backend vllm \
-          --model $model \
-          --dataset-name $dataset_name \
-          --dataset-path $dataset_path \
-          --sonnet-input-len $input_len \
-          --sonnet-output-len "$output_len" \
-          --sonnet-prefix-len $prefix_len \
-          --num-prompts $num_prompts \
-          --port 8100 \
-          --save-result \
-          --result-dir $results_folder \
-          --result-filename disagg_prefill_tp1.json \
-          --request-rate "inf"
+  vllm bench serve \
+    --backend vllm \
+    --model $model \
+    --dataset-name $dataset_name \
+    --dataset-path $dataset_path \
+    --sonnet-input-len $input_len \
+    --sonnet-output-len "$output_len" \
+    --sonnet-prefix-len $prefix_len \
+    --num-prompts $num_prompts \
+    --port 8100 \
+    --save-result \
+    --result-dir $results_folder \
+    --result-filename disagg_prefill_tp1.json \
+    --request-rate "inf"


  # send the request to decode.
  # The TTFT of this command will be the overhead of disagg prefill impl.
-  python3 ../benchmark_serving.py \
-          --backend vllm \
-          --model $model \
-          --dataset-name $dataset_name \
-          --dataset-path $dataset_path \
-          --sonnet-input-len $input_len \
-          --sonnet-output-len "$output_len" \
-          --sonnet-prefix-len $prefix_len \
-          --num-prompts $num_prompts \
-          --port 8200 \
-          --save-result \
-          --result-dir $results_folder \
-          --result-filename disagg_prefill_tp1_overhead.json \
-          --request-rate "$qps"
+  vllm bench serve \
+    --backend vllm \
+    --model $model \
+    --dataset-name $dataset_name \
+    --dataset-path $dataset_path \
+    --sonnet-input-len $input_len \
+    --sonnet-output-len "$output_len" \
+    --sonnet-prefix-len $prefix_len \
+    --num-prompts $num_prompts \
+    --port 8200 \
+    --save-result \
+    --result-dir $results_folder \
+    --result-filename disagg_prefill_tp1_overhead.json \
+    --request-rate "$qps"
  kill_gpu_processes

 }
--- a/benchmarks/disagg_benchmarks/disagg_performance_benchmark.sh
+++ b/benchmarks/disagg_benchmarks/disagg_performance_benchmark.sh
@ -18,6 +18,8 @@ kill_gpu_processes() {
  # kill all processes on GPU.
  pgrep pt_main_thread | xargs -r kill -9
  pgrep python3 | xargs -r kill -9
+  # vLLM now names the process with VLLM prefix after https://github.com/vllm-project/vllm/pull/21445
+  pgrep VLLM | xargs -r kill -9
  for port in 8000 8100 8200; do lsof -t -i:$port | xargs -r kill -9; done
  sleep 1
 }
@ -58,7 +60,7 @@ launch_chunked_prefill() {


 launch_disagg_prefill() {
-  model="meta-llama/Meta-Llama-3.1-8B-Instruct" 
+  model="meta-llama/Meta-Llama-3.1-8B-Instruct"
  # disagg prefill
  CUDA_VISIBLE_DEVICES=0 python3 \
    -m vllm.entrypoints.openai.api_server \
@ -97,20 +99,20 @@ benchmark() {
  output_len=$2
  tag=$3

-  python3 ../benchmark_serving.py \
-          --backend vllm \
-          --model $model \
-          --dataset-name $dataset_name \
-          --dataset-path $dataset_path \
-          --sonnet-input-len $input_len \
-          --sonnet-output-len "$output_len" \
-          --sonnet-prefix-len $prefix_len \
-          --num-prompts $num_prompts \
-          --port 8000 \
-          --save-result \
-          --result-dir $results_folder \
-          --result-filename "$tag"-qps-"$qps".json \
-          --request-rate "$qps"
+  vllm bench serve \
+    --backend vllm \
+    --model $model \
+    --dataset-name $dataset_name \
+    --dataset-path $dataset_path \
+    --sonnet-input-len $input_len \
+    --sonnet-output-len "$output_len" \
+    --sonnet-prefix-len $prefix_len \
+    --num-prompts $num_prompts \
+    --port 8000 \
+    --save-result \
+    --result-dir $results_folder \
+    --result-filename "$tag"-qps-"$qps".json \
+    --request-rate "$qps"

  sleep 2
 }
--- a/benchmarks/disagg_benchmarks/disagg_prefill_proxy_server.py
+++ b/benchmarks/disagg_benchmarks/disagg_prefill_proxy_server.py
@ -1,63 +1,199 @@
 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project

+import argparse
+import asyncio
+import logging
 import os

 import aiohttp
-from quart import Quart, make_response, request
+from quart import Quart, Response, make_response, request
+from rate_limiter import RateLimiter
+from request_queue import RequestQueue

-AIOHTTP_TIMEOUT = aiohttp.ClientTimeout(total=6 * 60 * 60)
-
-app = Quart(__name__)
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)


-async def forward_request(url, data):
-    async with aiohttp.ClientSession(timeout=AIOHTTP_TIMEOUT) as session:
+def parse_args():
+    """parse command line arguments"""
+    parser = argparse.ArgumentParser(description="vLLM P/D disaggregation proxy server")
+
+    # Add args
+    parser.add_argument(
+        "--timeout",
+        type=float,
+        default=300,
+        help="Timeout for backend service requests in seconds (default: 300)",
+    )
+    parser.add_argument(
+        "--max-concurrent",
+        type=int,
+        default=100,
+        help="Maximum concurrent requests to backend services (default: 100)",
+    )
+    parser.add_argument(
+        "--queue-size",
+        type=int,
+        default=500,
+        help="Maximum number of requests in the queue (default: 500)",
+    )
+    parser.add_argument(
+        "--rate-limit",
+        type=int,
+        default=40,
+        help="Maximum requests per second (default: 40)",
+    )
+    parser.add_argument(
+        "--port",
+        type=int,
+        default=8000,
+        help="Port to run the server on (default: 8000)",
+    )
+    parser.add_argument(
+        "--prefill-url",
+        type=str,
+        default="http://localhost:8100/v1/completions",
+        help="Prefill service endpoint URL",
+    )
+    parser.add_argument(
+        "--decode-url",
+        type=str,
+        default="http://localhost:8200/v1/completions",
+        help="Decode service endpoint URL",
+    )
+
+    return parser.parse_args()
+
+
+def main():
+    """parse command line arguments"""
+    args = parse_args()
+
+    # Initialize configuration using command line parameters
+    AIOHTTP_TIMEOUT = aiohttp.ClientTimeout(total=args.timeout)
+    MAX_CONCURRENT_REQUESTS = args.max_concurrent
+    REQUEST_QUEUE_SIZE = args.queue_size
+    RATE_LIMIT = args.rate_limit
+    PREFILL_SERVICE_URL = args.prefill_url
+    DECODE_SERVICE_URL = args.decode_url
+    PORT = args.port
+
+    app = Quart(__name__)
+
+    # Initialize the rate limiter and request queue
+    rate_limiter = RateLimiter(RATE_LIMIT)
+    request_queue = RequestQueue(MAX_CONCURRENT_REQUESTS, REQUEST_QUEUE_SIZE)
+
+    # Attach the configuration object to the application instance
+    app.config.update(
+        {
+            "AIOHTTP_TIMEOUT": AIOHTTP_TIMEOUT,
+            "rate_limiter": rate_limiter,
+            "request_queue": request_queue,
+            "PREFILL_SERVICE_URL": PREFILL_SERVICE_URL,
+            "DECODE_SERVICE_URL": DECODE_SERVICE_URL,
+        }
+    )
+
+    # Start queue processing on app startup
+    @app.before_serving
+    async def startup():
+        """Start request processing task when app starts serving"""
+        asyncio.create_task(request_queue.process())
+
+    async def forward_request(url, data):
+        """Forward request to backend service with rate limiting and error handling"""
        headers = {"Authorization": f"Bearer {os.environ.get('OPENAI_API_KEY')}"}
-        async with session.post(url=url, json=data, headers=headers) as response:
-            if response.status == 200:
-                # if response.headers.get('Transfer-Encoding') == 'chunked':
-                if True:
-                    async for chunk_bytes in response.content.iter_chunked(1024):
-                        yield chunk_bytes
-                else:
-                    content = await response.read()
-                    yield content

-
-@app.route("/v1/completions", methods=["POST"])
-async def handle_request():
-    try:
-        original_request_data = await request.get_json()
-
-        prefill_request = original_request_data.copy()
-        # change max_tokens = 1 to let it only do prefill
-        prefill_request["max_tokens"] = 1
-
-        # finish prefill
-        async for _ in forward_request(
-            "http://localhost:8100/v1/completions", prefill_request
+        # Use rate limiter as context manager
+        async with (
+            rate_limiter,
+            aiohttp.ClientSession(timeout=AIOHTTP_TIMEOUT) as session,
        ):
-            continue
+            try:
+                async with session.post(
+                    url=url, json=data, headers=headers
+                ) as response:
+                    if response.status == 200:
+                        # Stream response chunks
+                        async for chunk_bytes in response.content.iter_chunked(1024):
+                            yield chunk_bytes
+                    else:
+                        # Handle backend service errors
+                        error_text = await response.text()
+                        logger.error(
+                            "Backend service error: %s - %s",
+                            response.status,
+                            error_text,
+                        )
+                        yield b'{"error": "Backend service error"}'
+            except aiohttp.ClientError as e:
+                # Handle connection errors
+                logger.error("Connection error to %s: %s", url, str(e))
+                yield b'{"error": "Service unavailable"}'
+            except asyncio.TimeoutError:
+                # Handle timeout errors
+                logger.error("Timeout connecting to %s", url)
+                yield b'{"error": "Service timeout"}'

-        # return decode
-        generator = forward_request(
-            "http://localhost:8200/v1/completions", original_request_data
-        )
-        response = await make_response(generator)
-        response.timeout = None
+    async def process_request():
+        """Process a single request through prefill and decode stages"""
+        try:
+            original_request_data = await request.get_json()

-        return response
+            # Create prefill request (max_tokens=1)
+            prefill_request = original_request_data.copy()
+            prefill_request["max_tokens"] = 1

-    except Exception as e:
-        import sys
-        import traceback
+            # Execute prefill stage
+            async for _ in forward_request(PREFILL_SERVICE_URL, prefill_request):
+                continue

-        exc_info = sys.exc_info()
-        print("Error occurred in disagg prefill proxy server")
-        print(e)
-        print("".join(traceback.format_exception(*exc_info)))
+            # Execute decode stage and stream response
+            generator = forward_request(DECODE_SERVICE_URL, original_request_data)
+            response = await make_response(generator)
+            response.timeout = None  # Disable timeout for streaming response
+            return response
+
+        except Exception:
+            logger.exception("Error processing request")
+            return Response(
+                response=b'{"error": "Internal server error"}',
+                status=500,
+                content_type="application/json",
+            )
+
+    @app.route("/v1/completions", methods=["POST"])
+    async def handle_request():
+        """Handle incoming API requests with concurrency and rate limiting"""
+        # Create task for request processing
+        task = asyncio.create_task(process_request())
+
+        # Enqueue request or reject if queue is full
+        if not await request_queue.enqueue(task):
+            return Response(
+                response=b'{"error": "Server busy, try again later"}',
+                status=503,
+                content_type="application/json",
+            )
+
+        try:
+            # Return the response from the processing task
+            return await task
+        except asyncio.CancelledError:
+            # Handle task cancellation (timeout or queue full)
+            logger.warning("Request cancelled due to timeout or queue full")
+            return Response(
+                response=b'{"error": "Request cancelled"}',
+                status=503,
+                content_type="application/json",
+            )
+
+    # Start the Quart server with host can be set to 0.0.0.0
+    app.run(port=PORT)


 if __name__ == "__main__":
-    app.run(port=8000)
+    main()
--- a/benchmarks/disagg_benchmarks/rate_limiter.py
+++ b/benchmarks/disagg_benchmarks/rate_limiter.py
@ -0,0 +1,45 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+import asyncio
+import time
+
+
+class RateLimiter:
+    """Token bucket rate limiter implementation"""
+
+    def __init__(self, rate_limit):
+        self.rate_limit = rate_limit  # Requests per second
+        self.num_available_tokens = rate_limit  # Available tokens
+        self.last_refill = time.monotonic()  # Last token refill time
+        self.lock = asyncio.Lock()  # Synchronization lock
+
+    async def acquire(self):
+        """Acquire a token from the rate limiter"""
+        while True:
+            async with self.lock:
+                current_time = time.monotonic()
+                elapsed = current_time - self.last_refill
+
+                # Refill num_available_tokens if more than 1 second has passed
+                if elapsed > 1.0:
+                    self.num_available_tokens = self.rate_limit
+                    self.last_refill = current_time
+
+                # Check if num_available_tokens are available
+                if self.num_available_tokens > 0:
+                    self.num_available_tokens -= 1
+                    return True
+
+                # Calculate wait time if no num_available_tokens available
+                wait_time = 1.0 - elapsed
+            await asyncio.sleep(wait_time)
+
+    async def __aenter__(self):
+        """Enter async context manager - acquire token"""
+        await self.acquire()
+        return self
+
+    async def __aexit__(self, exc_type, exc_value, traceback):
+        """Exit async context manager - no cleanup needed"""
+        pass
--- a/benchmarks/disagg_benchmarks/request_queue.py
+++ b/benchmarks/disagg_benchmarks/request_queue.py
@ -0,0 +1,39 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+import asyncio
+from collections import deque
+
+
+class RequestQueue:
+    """Request queue manager with concurrency control"""
+
+    def __init__(self, max_concurrent, max_queue_size):
+        # Maximum concurrent requests
+        self.max_concurrent = max_concurrent
+        self.max_queue_size = max_queue_size  # Maximum queue size
+        # Concurrency control
+        self.semaphore = asyncio.Semaphore(max_concurrent)
+        self.queue = deque()  # Request queue
+        self.queue_size = 0  # Current queue size
+        self.lock = asyncio.Lock()  # Sync queue Lock
+
+    async def enqueue(self, task):
+        """Add a request task to the queue"""
+        async with self.lock:
+            if self.queue_size >= self.max_queue_size:
+                return False
+
+            self.queue.append(task)
+            self.queue_size += 1
+            return True
+
+    async def process(self):
+        """Process queued requests using semaphore for concurrency control"""
+        while True:
+            if self.queue:
+                async with self.semaphore, self.lock:
+                    task = self.queue.popleft()
+                    self.queue_size -= 1
+                    await task
+            await asyncio.sleep(0.01)  # Yield control to event loop
--- a/benchmarks/kernels/benchmark_aqlm.py
+++ b/benchmarks/kernels/benchmark_aqlm.py
@ -1,345 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-
-import os
-import sys
-from typing import Optional
-
-import torch
-import torch.nn.functional as F
-
-from vllm import _custom_ops as ops
-from vllm.model_executor.layers.quantization.aqlm import (
-    dequantize_weight,
-    generic_dequantize_gemm,
-    get_int_dtype,
-    optimized_dequantize_gemm,
-)
-from vllm.utils import FlexibleArgumentParser
-
-os.environ["CUDA_VISIBLE_DEVICES"] = "0"
-
-
-def torch_mult(
-    # [..., in_features]
-    input: torch.Tensor,
-    weights: torch.Tensor,
-    # [num_out_groups, 1, 1, 1]
-    scales: torch.Tensor,
-) -> torch.Tensor:
-    output = F.linear(input, weights)
-    return output
-
-
-def dequant_out_scale(
-    # [..., in_features]
-    input: torch.Tensor,
-    # [num_out_groups, num_in_groups, num_codebooks]
-    codes: torch.IntTensor,
-    # [num_codebooks, codebook_size, out_group_size, in_group_size]
-    codebooks: torch.Tensor,
-    # [num_out_groups, 1, 1, 1]
-    scales: torch.Tensor,
-    output_partition_sizes: torch.IntTensor,
-    bias: Optional[torch.Tensor],
-) -> torch.Tensor:
-    weights = ops.aqlm_dequant(codes, codebooks, output_partition_sizes)
-
-    if bias is None:
-        output = F.linear(input, weights, bias)
-        orig_shape = output.shape
-        flattened_output = output.view(-1, output.size(-1))
-        f_scales = scales.view(-1, scales.shape[0])
-        b_scales = f_scales.expand(flattened_output.shape[0], -1)
-        flattened_output *= b_scales
-        return flattened_output.view(orig_shape)
-    else:
-        b_scales = scales.view(scales.shape[:-3] + (-1,)).expand(-1, weights.shape[1])
-        weights *= b_scales
-        return F.linear(input, weights, bias)
-
-
-def dequant_weight_scale(
-    # [..., in_features]
-    input: torch.Tensor,
-    # [num_out_groups, num_in_groups, num_codebooks]
-    codes: torch.IntTensor,
-    # [num_codebooks, codebook_size, out_group_size, in_group_size]
-    codebooks: torch.Tensor,
-    # [num_out_groups, 1, 1, 1]
-    scales: torch.Tensor,
-    output_partition_sizes: torch.IntTensor,
-    bias: Optional[torch.Tensor],
-) -> torch.Tensor:
-    weights = ops.aqlm_dequant(codes, codebooks, output_partition_sizes)
-
-    b_scales = scales.view(scales.shape[:-3] + (-1,)).expand(-1, weights.shape[1])
-    weights *= b_scales
-    return F.linear(input, weights, bias)
-
-
-def dequant_no_scale(
-    # [..., in_features]
-    input: torch.Tensor,
-    # [num_out_groups, num_in_groups, num_codebooks]
-    codes: torch.IntTensor,
-    # [num_codebooks, codebook_size, out_group_size, in_group_size]
-    codebooks: torch.Tensor,
-    # [num_out_groups, 1, 1, 1]
-    scales: torch.Tensor,
-    output_partition_sizes: torch.IntTensor,
-    bias: Optional[torch.Tensor],
-) -> torch.Tensor:
-    weights = ops.aqlm_dequant(codes, codebooks, output_partition_sizes)
-
-    return F.linear(input, weights, bias)
-
-
-# Compare the optimized 1x16 and 2x8 cuda decompression/dequant kernels against
-# the generic pytorch version.
-# Just visual comparison.
-def dequant_test(k: int, parts: torch.Tensor, nbooks: int, bits: int) -> None:
-    n = int(parts.sum().item())
-
-    device = torch.device("cuda:0")
-
-    code_range = (1 << bits) // 2
-    ingroups = 8
-
-    codes = torch.randint(
-        -code_range,
-        code_range,
-        size=(n, k // ingroups, nbooks),
-        dtype=get_int_dtype(bits),
-        device=device,
-    )
-
-    codebooks = torch.randn(
-        size=(parts.shape[0] * nbooks, 1 << bits, 1, 8),
-        dtype=torch.float16,
-        device=device,
-    )
-
-    count = 0
-    for index in range(16):
-        for i in range(8):
-            for book in range(nbooks):
-                codebooks[book, index, 0, i] = count * (10**book)
-            count += 1
-
-    print("codes shape", codes.shape)
-
-    for i in range(16):
-        for book in range(nbooks):
-            codes[0, i, book] = i
-            codes[0, -i, book] = i
-
-    weights = dequantize_weight(codes, codebooks, None)
-    weights2 = ops.aqlm_dequant(codes, codebooks, parts)
-
-    print("weights shape:", weights.shape)
-    print("weights2 shape:", weights2.shape)
-
-    print("weights are:", weights)
-    print("weights2 are:", weights2)
-
-    print("first 128 weights are", weights[0, 0:128].to(torch.int32))
-    print("first 128 weights2 are:", weights2[0, 0:128].to(torch.int32))
-
-    print("last 128 weights are", weights[0, -128:])
-    print("last 128 weights2 are:", weights2[0, -128:])
-
-
-def main():
-    parser = FlexibleArgumentParser(description="Benchmark aqlm performance.")
-
-    # Add arguments
-    parser.add_argument(
-        "--nbooks", type=int, default=1, help="Number of codebooks (default: 1)"
-    )
-    parser.add_argument(
-        "--bits",
-        type=int,
-        default=16,
-        help="Number of bits per code element (default: 16)",
-    )
-    parser.add_argument(
-        "--test",
-        type=bool,
-        default=False,
-        help="Run the decompression/dequant tester rather than benchmarking "
-        "(default: False)",
-    )
-
-    # Parse the arguments
-    args = parser.parse_args()
-
-    # Extract values
-    nbooks = args.nbooks
-    bits = args.bits
-
-    if args.test:
-        dequant_test(4096, torch.tensor((4096,)), nbooks, bits)
-        return
-
-    # Otherwise, benchmark.
-    methods = [
-        ops.aqlm_gemm,
-        dequant_out_scale,
-        generic_dequantize_gemm,
-        optimized_dequantize_gemm,
-        dequant_weight_scale,
-        torch_mult,
-        dequant_no_scale,
-    ]
-
-    filename = f"./aqlm_benchmark_{nbooks}x{bits}.csv"
-    print(f"writing benchmarks to file {filename}")
-    with open(filename, "w") as f:
-        sys.stdout = f
-
-        print("m | k | n | n parts", end="")
-        for method in methods:
-            print(f" | {method.__name__.replace('_', ' ')} (µs)", end="")
-        print("")
-
-        # These are reasonable prefill sizes.
-        ksandpartions = (
-            (4096, (4096, 4096, 4096)),
-            (4096, (4096,)),
-            (4096, (11008, 11008)),
-            (11008, (4096,)),
-        )
-
-        # reasonable ranges for m.
-        for m in [
-            1,
-            2,
-            4,
-            8,
-            10,
-            12,
-            14,
-            16,
-            24,
-            32,
-            48,
-            52,
-            56,
-            64,
-            96,
-            112,
-            128,
-            256,
-            512,
-            1024,
-            1536,
-            2048,
-            3072,
-            4096,
-        ]:
-            print(f"{m}", file=sys.__stdout__)
-            for ksp in ksandpartions:
-                run_grid(m, ksp[0], torch.tensor(ksp[1]), nbooks, bits, methods)
-
-        sys.stdout = sys.__stdout__
-
-
-def run_grid(m: int, k: int, parts: torch.Tensor, nbooks: int, bits: int, methods):
-    # I didn't see visible improvements from increasing these, but feel free :)
-    num_warmup_trials = 1
-    num_trials = 1
-
-    num_calls = 100
-
-    # warmup.
-    for method in methods:
-        for _ in range(num_warmup_trials):
-            run_timing(
-                num_calls=num_calls,
-                m=m,
-                k=k,
-                parts=parts,
-                nbooks=nbooks,
-                bits=bits,
-                method=method,
-            )
-
-    n = parts.sum().item()
-    print(f"{m} | {k} | {n} | {parts.tolist()}", end="")
-
-    for method in methods:
-        best_time_us = 1e20
-        for _ in range(num_trials):
-            kernel_dur_ms = run_timing(
-                num_calls=num_calls,
-                m=m,
-                k=k,
-                parts=parts,
-                nbooks=nbooks,
-                bits=bits,
-                method=method,
-            )
-
-            kernel_dur_us = 1000 * kernel_dur_ms
-
-            if kernel_dur_us < best_time_us:
-                best_time_us = kernel_dur_us
-
-        print(f" | {kernel_dur_us:.0f}", end="")
-
-    print("")
-
-
-def run_timing(
-    num_calls: int, m: int, k: int, parts: torch.Tensor, nbooks: int, bits: int, method
-) -> float:
-    n = int(parts.sum().item())
-
-    device = torch.device("cuda:0")
-
-    input = torch.randn((1, m, k), dtype=torch.float16, device=device)
-
-    code_range = (1 << bits) // 2
-    ingroups = 8
-
-    codes = torch.randint(
-        -code_range,
-        code_range,
-        size=(n, k // ingroups, nbooks),
-        dtype=get_int_dtype(bits),
-        device=device,
-    )
-
-    codebooks = torch.randn(
-        size=(parts.shape[0] * nbooks, 1 << bits, 1, 8),
-        dtype=torch.float16,
-        device=device,
-    )
-
-    scales = torch.randn(size=(n, 1, 1, 1), dtype=torch.float16, device=device)
-
-    # for comparison to just a pytorch mult.
-    weights = torch.randn((n, k), dtype=torch.float16, device=device)
-
-    start_event = torch.cuda.Event(enable_timing=True)
-    end_event = torch.cuda.Event(enable_timing=True)
-
-    start_event.record()
-
-    if method is torch_mult:
-        for i in range(num_calls):
-            torch_mult(input, weights, scales)
-    else:
-        for i in range(num_calls):
-            method(input, codes, codebooks, scales, parts, None)
-
-    end_event.record()
-    end_event.synchronize()
-
-    dur_ms = start_event.elapsed_time(end_event) / num_calls
-    return dur_ms
-
-
-if __name__ == "__main__":
-    sys.exit(main())
--- a/benchmarks/kernels/benchmark_bitblas.py
+++ b/benchmarks/kernels/benchmark_bitblas.py
@ -3,6 +3,8 @@
 # Copyright (c) Microsoft Corporation.
 # Licensed under the MIT License.

+from packaging import version
+
 from vllm.model_executor.layers.quantization.utils.bitblas_utils import (
    MINIMUM_BITBLAS_VERSION,
 )
@ -10,7 +12,7 @@ from vllm.model_executor.layers.quantization.utils.bitblas_utils import (
 try:
    import bitblas

-    if bitblas.__version__ < MINIMUM_BITBLAS_VERSION:
+    if version.parse(bitblas.__version__) < version.parse(MINIMUM_BITBLAS_VERSION):
        raise ImportError(
            "bitblas version is wrong. Please "
            f"install bitblas>={MINIMUM_BITBLAS_VERSION}"
--- a/benchmarks/kernels/benchmark_grouped_gemm_cutlass.py
+++ b/benchmarks/kernels/benchmark_grouped_gemm_cutlass.py
@ -80,6 +80,11 @@ def bench_run(
        a, score, topk, renormalize=False
    )

+    ab_strides1 = torch.full((num_experts,), k, device="cuda", dtype=torch.int64)
+    ab_strides2 = torch.full((num_experts,), n, device="cuda", dtype=torch.int64)
+    c_strides1 = torch.full((num_experts,), 2 * n, device="cuda", dtype=torch.int64)
+    c_strides2 = torch.full((num_experts,), k, device="cuda", dtype=torch.int64)
+
    def run_triton_moe(
        a: torch.Tensor,
        w1: torch.Tensor,
@ -111,6 +116,10 @@ def bench_run(
        w2: torch.Tensor,
        w1_scale: torch.Tensor,
        w2_scale: torch.Tensor,
+        ab_strides1: torch.Tensor,
+        ab_strides2: torch.Tensor,
+        c_strides1: torch.Tensor,
+        c_strides2: torch.Tensor,
        topk_weights: torch.Tensor,
        topk_ids: torch.Tensor,
        per_act_token: bool,
@ -125,6 +134,10 @@ def bench_run(
                topk_ids,
                w1_scale,
                w2_scale,
+                ab_strides1,
+                ab_strides2,
+                c_strides1,
+                c_strides2,
                per_act_token,
                a1_scale=None,
            )
@ -136,6 +149,10 @@ def bench_run(
        w2_q: torch.Tensor,
        w1_scale: torch.Tensor,
        w2_scale: torch.Tensor,
+        ab_strides1: torch.Tensor,
+        ab_strides2: torch.Tensor,
+        c_strides1: torch.Tensor,
+        c_strides2: torch.Tensor,
        topk_weights: torch.Tensor,
        topk_ids: torch.Tensor,
    ):
@ -150,6 +167,10 @@ def bench_run(
                topk_ids,
                w1_scale,
                w2_scale,
+                ab_strides1,
+                ab_strides2,
+                c_strides1,
+                c_strides2,
                per_act_token,
                a1_scale=None,
            )
@ -194,6 +215,10 @@ def bench_run(
            w2_q,
            w1_scale,
            w2_scale,
+            ab_strides1,
+            ab_strides2,
+            c_strides1,
+            c_strides2,
            topk_weights,
            topk_ids,
        )
@ -231,6 +256,10 @@ def bench_run(
        "w1_scale": w1_scale,
        "w2_scale": w2_scale,
        "per_act_token": per_act_token,
+        "ab_strides1": ab_strides1,
+        "ab_strides2": ab_strides2,
+        "c_strides1": c_strides1,
+        "c_strides2": c_strides2,
        # cuda graph params
        "cutlass_graph": cutlass_graph,
        "triton_graph": triton_graph,
@ -289,6 +318,10 @@ def bench_run(
        w2_q,
        w1_scale,
        w2_scale,
+        ab_strides1,
+        ab_strides2,
+        c_strides1,
+        c_strides2,
        topk_weights,
        topk_ids,
        per_act_token,
@ -297,7 +330,7 @@ def bench_run(

    results.append(
        benchmark.Timer(
-            stmt="run_cutlass_moe(a, a_scale, w1_q, w2_q, w1_scale, w2_scale, topk_weights, topk_ids, per_act_token, num_runs)",  # noqa: E501
+            stmt="run_cutlass_moe(a, a_scale, w1_q, w2_q, w1_scale, w2_scale, ab_strides1, ab_strides2, c_strides1, c_strides2, topk_weights, topk_ids, per_act_token, num_runs)",  # noqa: E501
            globals=globals,
            label=label,
            sub_label=sub_label,
--- a/benchmarks/kernels/benchmark_machete.py
+++ b/benchmarks/kernels/benchmark_machete.py
@ -236,6 +236,7 @@ def marlin_create_bench_fn(bt: BenchmarkTensors) -> Callable:
            a=bt.a,
            c=None,
            b_q_weight=w_q,
+            b_bias=None,
            b_scales=w_s,
            global_scale=None,
            b_zeros=w_zp,
@ -252,28 +253,7 @@ def marlin_create_bench_fn(bt: BenchmarkTensors) -> Callable:
    else:
        assert bt.a.dtype == torch.int8
        assert bt.wtype == scalar_types.uint4b8
-
-        if bt.w_ch_s is not None:
-            s_ch = bt.w_ch_s.to(torch.float32)
-        else:
-            s_ch = torch.ones(bt.w_ref.shape[1], dtype=torch.float32, device=device)
-
-        if bt.w_tok_s is not None:
-            s_tok = bt.w_tok_s.to(torch.float32)
-        else:
-            s_tok = torch.ones(bt.a.shape[0], dtype=torch.float32, device=device)
-
-        fn = lambda: ops.marlin_qqq_gemm(
-            a=bt.a,
-            b_q_weight=w_q,
-            s_group=w_s,
-            s_tok=s_tok,
-            s_ch=s_ch,
-            workspace=workspace.scratch,
-            size_m=bt.a.shape[0],
-            size_n=bt.w_ref.shape[1],
-            size_k=bt.w_ref.shape[0],
-        )
+        raise NotImplementedError("QQQ is not supported anymore")

    return fn

--- a/benchmarks/kernels/benchmark_moe.py
+++ b/benchmarks/kernels/benchmark_moe.py
@ -3,6 +3,7 @@

 import argparse
 import json
+import os
 import time
 from contextlib import nullcontext
 from datetime import datetime
@ -22,6 +23,13 @@ from vllm.utils import FlexibleArgumentParser
 FP8_DTYPE = current_platform.fp8_dtype()


+def ensure_divisibility(numerator, denominator, text):
+    """Ensure that numerator is divisible by the denominator."""
+    assert numerator % denominator == 0, "{} {} is not divisible by tp {}.".format(
+        text, numerator, denominator
+    )
+
+
 class BenchmarkConfig(TypedDict):
    BLOCK_SIZE_M: int
    BLOCK_SIZE_N: int
@ -422,7 +430,6 @@ class BenchmarkWorker:
                hidden_size,
                topk,
                dtype_str,
-                is_marlin=False,
            )
        else:
            config = op_config[min(op_config.keys(), key=lambda x: abs(x - num_tokens))]
@ -535,6 +542,7 @@ def save_configs(
    use_fp8_w8a8: bool,
    use_int8_w8a16: bool,
    block_quant_shape: list[int],
+    save_dir: str,
 ) -> None:
    dtype_str = get_config_dtype_str(
        dtype, use_int8_w8a16=use_int8_w8a16, use_fp8_w8a8=use_fp8_w8a8
@ -545,7 +553,8 @@ def save_configs(
    filename = get_config_file_name(
        num_experts, shard_intermediate_size // 2, dtype_str, block_quant_shape
    )
-
+    os.makedirs(save_dir, exist_ok=True)
+    filename = os.path.join(save_dir, filename)
    print(f"Writing best config to {filename}...")
    with open(filename, "w") as f:
        json.dump(configs, f, indent=4)
@ -570,12 +579,10 @@ def main(args: argparse.Namespace):
        E = config.ffn_config.moe_num_experts
        topk = config.ffn_config.moe_top_k
        intermediate_size = config.ffn_config.ffn_hidden_size
-        shard_intermediate_size = 2 * intermediate_size // args.tp_size
    elif config.architectures[0] == "JambaForCausalLM":
        E = config.num_experts
        topk = config.num_experts_per_tok
        intermediate_size = config.intermediate_size
-        shard_intermediate_size = 2 * intermediate_size // args.tp_size
    elif config.architectures[0] in (
        "DeepseekV3ForCausalLM",
        "DeepseekV2ForCausalLM",
@ -584,17 +591,14 @@ def main(args: argparse.Namespace):
        E = config.n_routed_experts
        topk = config.num_experts_per_tok
        intermediate_size = config.moe_intermediate_size
-        shard_intermediate_size = 2 * intermediate_size // args.tp_size
    elif config.architectures[0] in ("Qwen2MoeForCausalLM", "Qwen3MoeForCausalLM"):
        E = config.num_experts
        topk = config.num_experts_per_tok
        intermediate_size = config.moe_intermediate_size
-        shard_intermediate_size = 2 * intermediate_size // args.tp_size
    elif config.architectures[0] in ("HunYuanMoEV1ForCausalLM"):
        E = config.num_experts
        topk = config.moe_topk[0]
        intermediate_size = config.moe_intermediate_size[0]
-        shard_intermediate_size = 2 * intermediate_size // args.tp_size
    else:
        # Support for llama4
        config = config.get_text_config()
@ -602,8 +606,14 @@ def main(args: argparse.Namespace):
        E = config.num_local_experts
        topk = config.num_experts_per_tok
        intermediate_size = config.intermediate_size
+    enable_ep = bool(args.enable_expert_parallel)
+    if enable_ep:
+        ensure_divisibility(E, args.tp_size, "Number of experts")
+        E = E // args.tp_size
+        shard_intermediate_size = 2 * intermediate_size
+    else:
+        ensure_divisibility(intermediate_size, args.tp_size, "intermediate_size")
        shard_intermediate_size = 2 * intermediate_size // args.tp_size
-
    hidden_size = config.hidden_size
    dtype = torch.float16 if current_platform.is_rocm() else config.torch_dtype
    use_fp8_w8a8 = args.dtype == "fp8_w8a8"
@ -699,6 +709,7 @@ def main(args: argparse.Namespace):
            use_fp8_w8a8,
            use_int8_w8a16,
            block_quant_shape,
+            args.save_dir,
        )
        end = time.time()
        print(f"Tuning took {end - start:.2f} seconds")
@ -735,10 +746,14 @@ if __name__ == "__main__":
    parser.add_argument(
        "--tp-size", "-tp", "--tensor-parallel-size", type=int, default=2
    )
+    parser.add_argument("--enable-expert-parallel", "-enable-ep", action="store_true")
    parser.add_argument(
        "--dtype", type=str, choices=["auto", "fp8_w8a8", "int8_w8a16"], default="auto"
    )
    parser.add_argument("--use-deep-gemm", action="store_true")
+    parser.add_argument(
+        "--save-dir", type=str, default="./", help="Directory to save tuned results"
+    )
    parser.add_argument("--seed", type=int, default=0)
    parser.add_argument("--batch-size", type=int, nargs="+", required=False)
    parser.add_argument("--tune", action="store_true")
--- a/benchmarks/kernels/benchmark_moe_align_block_size.py
+++ b/benchmarks/kernels/benchmark_moe_align_block_size.py
@ -5,9 +5,8 @@ import itertools

 import torch

-from vllm import _custom_ops as ops
 from vllm.model_executor.layers.fused_moe.moe_align_block_size import (
-    moe_align_block_size_triton,
+    moe_align_block_size,
 )
 from vllm.triton_utils import triton

@ -21,60 +20,6 @@ def get_topk_ids(num_tokens: int, num_experts: int, topk: int) -> torch.Tensor:
    )


-def check_correctness(num_tokens, num_experts=256, block_size=256, topk=8):
-    """
-    Verifies vllm vs. Triton
-    """
-    topk_ids = get_topk_ids(num_tokens, num_experts, topk)
-
-    # 1. malloc space for triton and vllm
-    # malloc enough space (max_num_tokens_padded) for the sorted ids
-    max_num_tokens_padded = topk_ids.numel() + num_experts * (block_size - 1)
-    sorted_ids_triton = torch.empty(
-        (max_num_tokens_padded,), dtype=torch.int32, device="cuda"
-    )
-    expert_ids_triton = torch.empty(
-        (max_num_tokens_padded // block_size,), dtype=torch.int32, device="cuda"
-    )
-    num_tokens_post_pad_triton = torch.empty((1,), dtype=torch.int32, device="cuda")
-
-    sorted_ids_vllm = torch.empty_like(sorted_ids_triton)
-    expert_ids_vllm = torch.empty_like(expert_ids_triton)
-    num_tokens_post_pad_vllm = torch.empty_like(num_tokens_post_pad_triton)
-
-    # 2. run implementations
-    moe_align_block_size_triton(
-        topk_ids,
-        num_experts,
-        block_size,
-        sorted_ids_triton,
-        expert_ids_triton,
-        num_tokens_post_pad_triton,
-    )
-
-    ops.moe_align_block_size(
-        topk_ids,
-        num_experts,
-        block_size,
-        sorted_ids_vllm,
-        expert_ids_vllm,
-        num_tokens_post_pad_vllm,
-    )
-    print(f"✅ VLLM implementation works with {num_experts} experts!")
-
-    # 3. compare results
-    if torch.allclose(expert_ids_triton, expert_ids_vllm) and torch.allclose(
-        num_tokens_post_pad_triton, num_tokens_post_pad_vllm
-    ):
-        print("✅ Triton and VLLM implementations match.")
-    else:
-        print("❌ Triton and VLLM implementations DO NOT match.")
-        print("Triton expert_ids:", expert_ids_triton)
-        print("VLLM expert_ids:", expert_ids_vllm)
-        print("Triton num_tokens_post_pad:", num_tokens_post_pad_triton)
-        print("VLLM num_tokens_post_pad:", num_tokens_post_pad_vllm)
-
-
 # test configurations
 num_tokens_range = [1, 16, 256, 4096]
 num_experts_range = [16, 64, 224, 256, 280, 512]
@ -87,8 +32,8 @@ configs = list(itertools.product(num_tokens_range, num_experts_range, topk_range
        x_names=["num_tokens", "num_experts", "topk"],
        x_vals=configs,
        line_arg="provider",
-        line_vals=["vllm", "triton"],  # "triton"
-        line_names=["VLLM", "Triton"],  # "Triton"
+        line_vals=["vllm"],
+        line_names=["vLLM"],
        plot_name="moe-align-block-size-performance",
        args={},
    )
@ -98,36 +43,11 @@ def benchmark(num_tokens, num_experts, topk, provider):
    block_size = 256
    topk_ids = get_topk_ids(num_tokens, num_experts, topk)

-    max_num_tokens_padded = topk_ids.numel() + num_experts * (block_size - 1)
-    sorted_ids = torch.empty((max_num_tokens_padded,), dtype=torch.int32, device="cuda")
-    max_num_m_blocks = max_num_tokens_padded // block_size
-    expert_ids = torch.empty((max_num_m_blocks,), dtype=torch.int32, device="cuda")
-    num_tokens_post_pad = torch.empty((1,), dtype=torch.int32, device="cuda")
-
    quantiles = [0.5, 0.2, 0.8]

    if provider == "vllm":
        ms, min_ms, max_ms = triton.testing.do_bench(
-            lambda: ops.moe_align_block_size(
-                topk_ids,
-                num_experts,
-                block_size,
-                sorted_ids.clone(),
-                expert_ids.clone(),
-                num_tokens_post_pad.clone(),
-            ),
-            quantiles=quantiles,
-        )
-    elif provider == "triton":
-        ms, min_ms, max_ms = triton.testing.do_bench(
-            lambda: moe_align_block_size_triton(
-                topk_ids,
-                num_experts,
-                block_size,
-                sorted_ids.clone(),
-                expert_ids.clone(),
-                num_tokens_post_pad.clone(),
-            ),
+            lambda: moe_align_block_size(topk_ids, block_size, num_experts),
            quantiles=quantiles,
        )

@ -151,6 +71,4 @@ if __name__ == "__main__":
    )
    args = parser.parse_args()

-    print("Running correctness check...")
-    check_correctness(num_tokens=1024, num_experts=args.num_experts, topk=args.topk)
    benchmark.run(print_data=True, show_plots=True)
--- a/benchmarks/kernels/benchmark_moe_permute_unpermute.py
+++ b/benchmarks/kernels/benchmark_moe_permute_unpermute.py
@ -8,12 +8,13 @@ import ray
 import torch
 from transformers import AutoConfig

-from vllm.model_executor.layers.fused_moe.deep_gemm_moe import (
+from vllm.model_executor.layers.fused_moe.fused_moe import *
+from vllm.model_executor.layers.fused_moe.moe_permute_unpermute import (
    _moe_permute,
    _moe_unpermute_and_reduce,
+    moe_permute,
+    moe_unpermute,
 )
-from vllm.model_executor.layers.fused_moe.fused_moe import *
-from vllm.model_executor.layers.fused_moe.moe_permute_unpermute import *
 from vllm.model_executor.layers.fused_moe.utils import _fp8_quantize
 from vllm.platforms import current_platform
 from vllm.utils import FlexibleArgumentParser
@ -63,18 +64,19 @@ def benchmark_permute(

    def run():
        if use_customized_permute:
-            (permuted_hidden_states, first_token_off, inv_perm_idx, m_indices) = (
-                moe_permute(
-                    qhidden_states,
-                    topk_weights=topk_weights,
-                    topk_ids=topk_ids,
-                    token_expert_indices=token_expert_indices,
-                    topk=topk,
-                    n_expert=num_experts,
-                    n_local_expert=num_experts,
-                    expert_map=None,
-                    align_block_size=align_block_size,
-                )
+            (
+                permuted_hidden_states,
+                a1q_scale,
+                first_token_off,
+                inv_perm_idx,
+                m_indices,
+            ) = moe_permute(
+                qhidden_states,
+                a1q_scale=None,
+                topk_ids=topk_ids,
+                n_expert=num_experts,
+                expert_map=None,
+                align_block_size=align_block_size,
            )
        else:
            (
@ -150,18 +152,19 @@ def benchmark_unpermute(

    def prepare():
        if use_customized_permute:
-            (permuted_hidden_states, first_token_off, inv_perm_idx, m_indices) = (
-                moe_permute(
-                    qhidden_states,
-                    topk_weights=topk_weights,
-                    topk_ids=topk_ids,
-                    token_expert_indices=token_expert_indices,
-                    topk=topk,
-                    n_expert=num_experts,
-                    n_local_expert=num_experts,
-                    expert_map=None,
-                    align_block_size=align_block_size,
-                )
+            (
+                permuted_hidden_states,
+                a1q_scale,
+                first_token_off,
+                inv_perm_idx,
+                m_indices,
+            ) = moe_permute(
+                qhidden_states,
+                a1q_scale=None,
+                topk_ids=topk_ids,
+                n_expert=num_experts,
+                expert_map=None,
+                align_block_size=align_block_size,
            )
            # convert to fp16/bf16 as gemm output
            return (
@ -191,16 +194,19 @@ def benchmark_unpermute(

    def run(input: tuple):
        if use_customized_permute:
-            (permuted_hidden_states, first_token_off, inv_perm_idx, m_indices) = input
+            (
+                permuted_hidden_states,
+                first_token_off,
+                inv_perm_idx,
+                m_indices,
+            ) = input
+            output = torch.empty_like(hidden_states)
            moe_unpermute(
+                output,
                permuted_hidden_states,
                topk_weights,
-                topk_ids,
                inv_perm_idx,
                first_token_off,
-                topk,
-                num_experts,
-                num_experts,
            )
        else:
            (
@ -211,7 +217,11 @@ def benchmark_unpermute(
                inv_perm,
            ) = input
            _moe_unpermute_and_reduce(
-                output_hidden_states, permuted_hidden_states, inv_perm, topk_weights
+                output_hidden_states,
+                permuted_hidden_states,
+                inv_perm,
+                topk_weights,
+                True,
            )

    # JIT compilation & warmup
--- a/benchmarks/kernels/benchmark_mrope.py
+++ b/benchmarks/kernels/benchmark_mrope.py
@ -0,0 +1,328 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+# This script benchmarks the mrope kernel (mainly for Qwen2VL and Qwen2.5VL models).
+# It generates test data, runs benchmarks, and saves results to a CSV file.
+#
+# The CSV file (named with current date/time) contains these columns:
+# model_name, tp_size, num_tokens, num_heads, num_kv_heads, head_dim, max_position,
+# rope_theta, is_neox_style, rope_scaling, dtype, torch_mean, torch_median, torch_p99,
+# torch_min, torch_max, triton_mean, triton_median, triton_p99, triton_min, triton_max,
+# speedup
+#
+# == Usage Examples ==
+#
+# Single model benchmark:
+# python3 benchmark_mrope.py --model-name Qwen/Qwen2-VL-7B-Instruct --tp-size 1 \
+#   --warmup-iter 10 --benchmark-iter 100 --dtype bfloat16 --seed 0 --num-tokens 1024
+#
+# All models benchmark:
+# python3 benchmark_mrope.py --model-name "" --tp-size 1 --warmup-iter 10 \
+#   --benchmark-iter 100 --dtype bfloat16 --seed 0 --num-tokens 1024
+#
+# All models with different TP sizes:
+# python3 benchmark_mrope.py --model-name "" --tp-size 1 2 4 8 --warmup-iter 10 \
+#   --benchmark-iter 100 --dtype bfloat16 --seed 0 --num-tokens 1024
+#
+# All models with different token counts:
+# python3 benchmark_mrope.py --model-name "" --tp-size 1 --warmup-iter 10 \
+#   --benchmark-iter 100 --dtype bfloat16 --seed 0 --num-tokens 1024 4096 16384
+import csv
+import os
+import time
+from datetime import datetime
+from typing import Any
+
+import numpy as np
+import torch
+
+from vllm.model_executor.layers.rotary_embedding import get_rope
+from vllm.platforms import current_platform
+from vllm.transformers_utils.config import get_config
+from vllm.utils import FlexibleArgumentParser
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+
+def generate_test_data(
+    num_tokens: int,
+    num_q_heads: int,
+    num_kv_heads: int,
+    head_size: int,
+    max_position_embeddings: int,
+    dtype: torch.dtype,
+    device: torch.device,
+):
+    """Generate test data for given configuration."""
+    # Create 2D positions (3, num_tokens) for multimodal case
+    positions = torch.randint(
+        0, max_position_embeddings // 4, (3, num_tokens), device=device
+    )
+
+    # Create query and key tensors
+    query = torch.randn(num_tokens, num_q_heads * head_size, dtype=dtype, device=device)
+    key = torch.randn(num_tokens, num_kv_heads * head_size, dtype=dtype, device=device)
+
+    return positions, query, key
+
+
+def calculate_stats(times: list[float]) -> dict[str, float]:
+    """Calculate statistics from a list of times."""
+    times_array = np.array(times)
+    return {
+        "mean": np.mean(times_array),
+        "median": np.median(times_array),
+        "p99": np.percentile(times_array, 99),
+        "min": np.min(times_array),
+        "max": np.max(times_array),
+    }
+
+
+def benchmark_mrope(
+    model_name: str,
+    num_tokens: int,
+    head_dim: int,
+    tp_size: int,
+    num_heads: int,
+    num_kv_heads: int,
+    max_position: int = 8192,
+    rope_theta: float = 10000,
+    is_neox_style: bool = True,
+    rope_scaling: dict[str, Any] = None,
+    dtype: torch.dtype = torch.bfloat16,
+    seed: int = 0,
+    warmup_iter: int = 10,
+    benchmark_iter: int = 100,
+    csv_writer=None,
+):
+    current_platform.seed_everything(seed)
+    torch.set_default_device(device)
+    # the parameters to compute the q k v size based on tp_size
+    mrope_helper_class = get_rope(
+        head_size=head_dim,
+        rotary_dim=head_dim,
+        max_position=max_position,
+        base=rope_theta,
+        is_neox_style=is_neox_style,
+        rope_scaling=rope_scaling,
+        dtype=dtype,
+    ).to(device=device)
+
+    print(80 * "=")
+    print(
+        f"Evaluating model: {model_name} "
+        f"with tp_size: {tp_size} "
+        f"and num_tokens: {num_tokens}, "
+        f"dtype: {dtype}"
+    )
+
+    # create q k v input tensors
+    # create rotary pos emb input tensors
+    positions, query, key = generate_test_data(
+        num_tokens, num_heads, num_kv_heads, head_dim, max_position, dtype, device
+    )
+
+    # Warm up
+    for _ in range(warmup_iter):
+        mrope_helper_class.forward_native(
+            positions,
+            query.clone(),
+            key.clone(),
+        )
+
+        mrope_helper_class.forward_cuda(
+            positions,
+            query.clone(),
+            key.clone(),
+        )
+
+    torch.cuda.synchronize()
+
+    # Time reference implementation
+    torch_times = []
+    for _ in range(benchmark_iter):
+        query_clone = query.clone()
+        key_clone = key.clone()
+        torch.cuda.synchronize()
+        start_time = time.time()
+
+        mrope_helper_class.forward_native(
+            positions,
+            query_clone,
+            key_clone,
+        )
+
+        torch.cuda.synchronize()
+        torch_times.append(time.time() - start_time)
+
+    # Time triton kernel implementation
+    triton_times = []
+    for _ in range(benchmark_iter):
+        query_clone = query.clone()
+        key_clone = key.clone()
+        torch.cuda.synchronize()
+        start_time = time.time()
+        mrope_helper_class.forward_cuda(
+            positions,
+            query_clone,
+            key_clone,
+        )
+        torch.cuda.synchronize()
+        triton_times.append(time.time() - start_time)
+
+    # Calculate statistics
+    torch_stats = calculate_stats(torch_times)
+    triton_stats = calculate_stats(triton_times)
+    print(f"\nPerformance for config ({num_tokens}, {num_heads}, {num_kv_heads}):")
+
+    print(
+        f"Torch implementation: "
+        f"mean={torch_stats['mean']:.8f}s, "
+        f"median={torch_stats['median']:.8f}s, "
+        f"p99={torch_stats['p99']:.8f}s"
+    )
+
+    print(
+        f"Triton implementation: "
+        f"mean={triton_stats['mean']:.8f}s, "
+        f"median={triton_stats['median']:.8f}s, "
+        f"p99={triton_stats['p99']:.8f}s"
+    )
+
+    print(
+        f"Triton Speedup over Torch: {torch_stats['mean'] / triton_stats['mean']:.8f}x"
+    )
+
+    # Write to CSV
+    if csv_writer:
+        row = [
+            model_name,
+            tp_size,
+            num_tokens,
+            num_heads,
+            num_kv_heads,
+            head_dim,
+            max_position,
+            rope_theta,
+            is_neox_style,
+            str(rope_scaling),
+            str(dtype).split(".")[-1],
+            torch_stats["mean"],
+            torch_stats["median"],
+            torch_stats["p99"],
+            torch_stats["min"],
+            torch_stats["max"],
+            triton_stats["mean"],
+            triton_stats["median"],
+            triton_stats["p99"],
+            triton_stats["min"],
+            triton_stats["max"],
+            torch_stats["mean"] / triton_stats["mean"],  # speedup
+        ]
+        csv_writer.writerow(row)
+
+    return torch_stats, triton_stats
+
+
+if __name__ == "__main__":
+    parser = FlexibleArgumentParser(
+        description="Benchmark the rotary embedding kernels."
+    )
+    parser.add_argument("--model-name", type=str, default="")
+    parser.add_argument("--tp-size", type=int, default=1)
+    parser.add_argument("--warmup-iter", type=int, default=10)
+    parser.add_argument("--benchmark-iter", type=int, default=100)
+    parser.add_argument("--dtype", type=str, choices=["bfloat16"], default="bfloat16")
+    parser.add_argument("--seed", type=int, default=0)
+    parser.add_argument("--num-tokens", type=int, nargs="+", required=False)
+    parser.add_argument("--trust-remote-code", action="store_true")
+    parser.add_argument("--output-csv", type=str, default="mrope_benchmark_results.csv")
+    args = parser.parse_args()
+    print(args)
+
+    # Create CSV file for results
+    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+    csv_filename = f"{os.path.splitext(args.output_csv)[0]}_{timestamp}.csv"
+
+    with open(csv_filename, "w", newline="") as csvfile:
+        csv_writer = csv.writer(csvfile)
+        # Write header
+        header = [
+            "model_name",
+            "tp_size",
+            "num_tokens",
+            "num_heads",
+            "num_kv_heads",
+            "head_dim",
+            "max_position",
+            "rope_theta",
+            "is_neox_style",
+            "rope_scaling",
+            "dtype",
+            "torch_mean",
+            "torch_median",
+            "torch_p99",
+            "torch_min",
+            "torch_max",
+            "triton_mean",
+            "triton_median",
+            "triton_p99",
+            "triton_min",
+            "triton_max",
+            "speedup",
+        ]
+        csv_writer.writerow(header)
+
+        model_tp_dict = {}
+        if args.model_name == "":
+            model_tp_dict = {
+                "Qwen/Qwen2-VL-2B-Instruct": [1],
+                "Qwen/Qwen2-VL-7B-Instruct": [1],
+                "Qwen/Qwen2-VL-72B-Instruct": [2, 4, 8],
+                "Qwen/Qwen2.5-VL-3B-Instruct": [1, 2, 4, 8],
+                "Qwen/Qwen2.5-VL-7B-Instruct": [1, 2, 4, 8],
+                "Qwen/Qwen2.5-VL-72B-Instruct": [2, 4, 8],
+            }
+        else:
+            model_tp_dict[args.model_name] = [args.tp_size]
+
+        if args.num_tokens is None:
+            num_tokens_list = [2**i for i in range(0, 18)]
+        else:
+            num_tokens_list = args.num_tokens
+
+        for model_name, tp_list in model_tp_dict.items():
+            config = get_config(model_name, trust_remote_code=args.trust_remote_code)
+            for tp_size in tp_list:
+                # get the model config
+                total_num_kv_heads = config.num_key_value_heads
+                total_num_heads = config.num_attention_heads
+                num_heads = total_num_heads // tp_size
+                num_kv_heads = max(1, total_num_kv_heads // tp_size)
+                head_dim = config.hidden_size // total_num_heads
+                q_size = num_heads * head_dim
+                kv_size = num_kv_heads * head_dim
+                is_neox_style = True
+                rope_theta = config.rope_theta
+                max_position = config.max_position_embeddings
+
+                for num_tokens in num_tokens_list:
+                    benchmark_mrope(
+                        model_name=model_name,
+                        num_tokens=num_tokens,
+                        head_dim=head_dim,
+                        tp_size=tp_size,
+                        num_heads=num_heads,
+                        num_kv_heads=num_kv_heads,
+                        max_position=max_position,
+                        rope_theta=rope_theta,
+                        is_neox_style=is_neox_style,
+                        rope_scaling=config.rope_scaling,
+                        dtype=getattr(torch, args.dtype),
+                        seed=args.seed,
+                        warmup_iter=args.warmup_iter,
+                        benchmark_iter=args.benchmark_iter,
+                        csv_writer=csv_writer,
+                    )
+
+    print(f"Benchmark results saved to {csv_filename}")
--- a/benchmarks/kernels/benchmark_per_token_group_quant.py
+++ b/benchmarks/kernels/benchmark_per_token_group_quant.py
@ -0,0 +1,159 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+import argparse
+import math
+from contextlib import contextmanager
+from typing import Callable
+from unittest.mock import patch
+
+import torch
+
+from vllm.model_executor.layers.quantization.utils import fp8_utils, int8_utils
+from vllm.platforms import current_platform
+
+
+@contextmanager
+def _triton_mode():
+    """Temporarily force the Triton fallback path"""
+    with patch("vllm.platforms.current_platform.is_cuda", return_value=False):
+        yield
+
+
+def _time_cuda(
+    fn: Callable[[], tuple[torch.Tensor, torch.Tensor]],
+    warmup_iters: int,
+    bench_iters: int,
+) -> float:
+    # warmup
+    for _ in range(warmup_iters):
+        fn()
+    torch.cuda.synchronize()
+
+    start = torch.cuda.Event(enable_timing=True)
+    end = torch.cuda.Event(enable_timing=True)
+
+    start.record()
+    for _ in range(bench_iters):
+        fn()
+    end.record()
+    torch.cuda.synchronize()
+
+    return start.elapsed_time(end) / bench_iters  # ms/iter
+
+
+def _run_single(
+    shape: tuple[int, int],
+    group_size: int,
+    dtype: str,
+    *,
+    column_major: bool = False,
+    scale_ue8m0: bool = False,
+    warmup_iters: int,
+    bench_iters: int,
+) -> None:
+    num_tokens, hidden_dim = shape
+
+    device = torch.device("cuda")
+    torch.manual_seed(42)
+    x = torch.randn(num_tokens, hidden_dim, device=device, dtype=torch.bfloat16) * 8
+
+    if dtype == "fp8":
+
+        def cuda_impl():
+            return fp8_utils.per_token_group_quant_fp8(
+                x,
+                group_size,
+                column_major_scales=column_major,
+                use_ue8m0=scale_ue8m0,
+            )
+
+        def triton_impl():
+            with _triton_mode():
+                return fp8_utils.per_token_group_quant_fp8(
+                    x,
+                    group_size,
+                    column_major_scales=column_major,
+                    use_ue8m0=scale_ue8m0,
+                )
+    elif dtype == "int8":
+
+        def cuda_impl():
+            return int8_utils.per_token_group_quant_int8(x, group_size)
+
+        def triton_impl():
+            with _triton_mode():
+                return int8_utils.per_token_group_quant_int8(x, group_size)
+    else:
+        raise ValueError("dtype must be 'fp8' or 'int8'")
+
+    cuda_ms = _time_cuda(cuda_impl, warmup_iters, bench_iters)
+    triton_ms = _time_cuda(triton_impl, warmup_iters, bench_iters)
+
+    speedup = triton_ms / cuda_ms if cuda_ms else math.inf
+
+    cfg_desc = (
+        f"shape={shape}  gs={group_size:<3}  col_major={column_major:<5}  "
+        f"ue8m0={scale_ue8m0:<5}  dtype={dtype}"
+    )
+    print(
+        f"{cfg_desc:55} | CUDA {cuda_ms:7.3f} ms  | Triton {triton_ms:7.3f} ms  | "
+        f"speed-up ×{speedup:5.2f}"
+    )
+
+
+def parse_args():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--warmup-iters", type=int, default=10)
+    parser.add_argument("--bench-iters", type=int, default=100)
+    parser.add_argument("--dtype", choices=["fp8", "int8", "both"], default="both")
+    return parser.parse_args()
+
+
+if __name__ == "__main__":
+    if not current_platform.is_cuda():
+        raise RuntimeError("CUDA device is required to run this benchmark.")
+
+    args = parse_args()
+    warmup_iters, bench_iters = args.warmup_iters, args.bench_iters
+
+    shapes = [(32, 128), (64, 256), (16, 512)]
+    group_sizes = [64, 128]
+
+    dtypes = ["fp8", "int8"] if args.dtype == "both" else [args.dtype]
+
+    header = (
+        "Configuration".ljust(55)
+        + " | "
+        + "CUDA (ms)".center(12)
+        + " | "
+        + "Triton (ms)".center(13)
+        + " | "
+        + "Speed-up"
+    )
+    print(header)
+    print("-" * len(header))
+
+    for dtype in dtypes:
+        for shape in shapes:
+            for gs in group_sizes:
+                if dtype == "fp8":
+                    for col_major in (False, True):
+                        for ue8m0 in (False, True):
+                            _run_single(
+                                shape,
+                                gs,
+                                dtype,
+                                column_major=col_major,
+                                scale_ue8m0=ue8m0,
+                                warmup_iters=warmup_iters,
+                                bench_iters=bench_iters,
+                            )
+                else:  # INT8 has no col-major / ue8m0 switches
+                    _run_single(
+                        shape,
+                        gs,
+                        dtype,
+                        warmup_iters=warmup_iters,
+                        bench_iters=bench_iters,
+                    )
--- a/benchmarks/kernels/benchmark_reshape_and_cache_flash.py
+++ b/benchmarks/kernels/benchmark_reshape_and_cache_flash.py
@ -0,0 +1,156 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+from __future__ import annotations
+
+import random
+import time
+
+import torch
+from tabulate import tabulate
+
+from vllm import _custom_ops as ops
+from vllm.logger import init_logger
+from vllm.platforms import current_platform
+from vllm.utils import (
+    STR_DTYPE_TO_TORCH_DTYPE,
+    FlexibleArgumentParser,
+    create_kv_caches_with_random_flash,
+)
+
+logger = init_logger(__name__)
+
+
+@torch.inference_mode()
+def run_benchmark(
+    num_tokens: int,
+    num_heads: int,
+    head_size: int,
+    block_size: int,
+    num_blocks: int,
+    dtype: torch.dtype,
+    kv_cache_dtype: str,
+    kv_cache_layout: str,
+    num_iters: int,
+    device: str = "cuda",
+) -> float:
+    """Return latency (seconds) for given num_tokens."""
+
+    if kv_cache_dtype == "fp8" and head_size % 16:
+        raise ValueError("fp8 kv-cache requires head_size to be a multiple of 16.")
+
+    current_platform.seed_everything(42)
+    torch.set_default_device(device)
+
+    # create random key / value tensors [T, H, D].
+    key = torch.randn(num_tokens, num_heads, head_size, dtype=dtype, device=device)
+    value = torch.randn_like(key)
+
+    # prepare the slot mapping.
+    # each token is assigned a unique slot in the KV-cache.
+    num_slots = block_size * num_blocks
+    if num_tokens > num_slots:
+        raise ValueError("num_tokens cannot exceed the total number of cache slots")
+    slot_mapping_lst = random.sample(range(num_slots), num_tokens)
+    slot_mapping = torch.tensor(slot_mapping_lst, dtype=torch.long, device=device)
+
+    key_caches, value_caches = create_kv_caches_with_random_flash(
+        num_blocks,
+        block_size,
+        1,  # num_layers
+        num_heads,
+        head_size,
+        kv_cache_dtype,
+        dtype,
+        device=device,
+        cache_layout=kv_cache_layout,
+    )
+    key_cache, value_cache = key_caches[0], value_caches[0]
+
+    # compute per-kernel scaling factors for fp8 conversion (if used).
+    k_scale = (key.amax() / 64.0).to(torch.float32)
+    v_scale = (value.amax() / 64.0).to(torch.float32)
+
+    def run_cuda_benchmark(n_iters: int) -> float:
+        nonlocal key, value, key_cache, value_cache, slot_mapping
+        torch.cuda.synchronize()
+        start = time.perf_counter()
+        for _ in range(n_iters):
+            ops.reshape_and_cache_flash(
+                key,
+                value,
+                key_cache,
+                value_cache,
+                slot_mapping,
+                kv_cache_dtype,
+                k_scale,
+                v_scale,
+            )
+        torch.cuda.synchronize()
+        end = time.perf_counter()
+        return (end - start) / n_iters
+
+    # warm-up
+    run_cuda_benchmark(3)
+
+    lat = run_cuda_benchmark(num_iters)
+
+    # free tensors to mitigate OOM when sweeping
+    del key, value, key_cache, value_cache, slot_mapping
+    torch.cuda.empty_cache()
+
+    return lat
+
+
+def main(args):
+    rows = []
+    for layout in ["NHD", "HND"]:
+        for exp in range(1, 17):
+            n_tok = 2**exp
+            lat = run_benchmark(
+                num_tokens=n_tok,
+                num_heads=args.num_heads,
+                head_size=args.head_size,
+                block_size=args.block_size,
+                num_blocks=args.num_blocks,
+                dtype=STR_DTYPE_TO_TORCH_DTYPE[args.dtype],
+                kv_cache_dtype=args.kv_cache_dtype,
+                kv_cache_layout=layout,
+                num_iters=args.iters,
+                device="cuda",
+            )
+            rows.append([n_tok, layout, f"{lat * 1e6:.3f}"])
+
+    print(tabulate(rows, headers=["num_tokens", "layout", "latency (µs)"]))
+
+
+if __name__ == "__main__":
+    parser = FlexibleArgumentParser()
+
+    parser.add_argument("--num-heads", type=int, default=128)
+    parser.add_argument(
+        "--head-size",
+        type=int,
+        choices=[64, 80, 96, 112, 120, 128, 192, 256],
+        default=128,
+    )
+    parser.add_argument("--block-size", type=int, choices=[16, 32], default=16)
+    parser.add_argument("--num-blocks", type=int, default=128 * 512)
+
+    parser.add_argument(
+        "--dtype",
+        type=str,
+        choices=["half", "bfloat16", "float"],
+        default="bfloat16",
+    )
+
+    parser.add_argument(
+        "--kv-cache-dtype",
+        type=str,
+        choices=["auto", "fp8"],
+        default="auto",
+    )
+
+    parser.add_argument("--iters", type=int, default=100)
+    args = parser.parse_args()
+
+    main(args)
--- a/benchmarks/kernels/benchmark_trtllm_attention.py
+++ b/benchmarks/kernels/benchmark_trtllm_attention.py
@ -1,240 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-
-import csv
-import os
-import random
-from datetime import datetime
-
-import flashinfer
-import torch
-
-FLOAT32_BYTES = torch.finfo(torch.float).bits // 8
-
-# KV Cache Layout for TRT-LLM
-# kv_cache_shape = (num_blocks, 2, num_kv_heads, page_size, head_dim)
-
-
-def to_float8(x, dtype=torch.float8_e4m3fn):
-    finfo = torch.finfo(dtype)
-    min_val, max_val = x.aminmax()
-    amax = torch.maximum(min_val.abs(), max_val.abs()).clamp(min=1e-12)
-    scale = finfo.max / amax * 0.1
-    x_scl_sat = (x * scale).clamp(min=finfo.min, max=finfo.max)
-    return x_scl_sat.to(dtype), scale.float().reciprocal()
-
-
-@torch.no_grad()
-def benchmark_decode(
-    num_seqs,
-    max_seq_len,
-    page_size=16,
-    dtype=torch.bfloat16,
-    kv_layout="HND",
-    num_kv_heads=8,
-    kv_cache_dtype="auto",
-    head_dim=128,
-    warmup=10,
-    trials=20,
-):
-    torch.set_default_device("cuda")
-    device = "cuda"
-    torch.manual_seed(0)
-
-    # Currently only HEAD_GRP_SIZE == 8 is supported
-    HEAD_GRP_SIZE = 8
-    MAX_SEQ_LEN = max_seq_len
-
-    # large number to reduce kv_cache reuse
-    NUM_BLOCKS = int(256000 / page_size)
-
-    workspace_buffer = torch.empty(1024 * 1024 * 1024, dtype=torch.int8, device=device)
-
-    # For decode, batch_size is num_decode_token
-    num_qo_heads = num_kv_heads * HEAD_GRP_SIZE
-    sm_scale = float(1.0 / (head_dim**0.5))
-    q = torch.randn(num_seqs, num_qo_heads, head_dim, device=device, dtype=dtype)
-    kv_lens = [random.randint(1, MAX_SEQ_LEN) for _ in range(num_seqs)]
-
-    max_kv_len = max(kv_lens)
-    kv_lens_tensor = torch.tensor(kv_lens, dtype=torch.int, device=device)
-    max_num_blocks_per_seq = (max_kv_len + page_size - 1) // page_size
-
-    block_tables = torch.randint(
-        0, NUM_BLOCKS, (num_seqs, max_num_blocks_per_seq), dtype=torch.int32
-    )
-
-    kv_cache_shape = (NUM_BLOCKS, 2, num_kv_heads, page_size, head_dim)
-    kv_cache = torch.randn(size=kv_cache_shape, device=device, dtype=dtype)
-    k_scale = v_scale = 1.0
-
-    if kv_cache_dtype.startswith("fp8"):
-        kv_cache, _ = to_float8(kv_cache)
-
-    # Benchmark TRT decode
-    def trt_decode():
-        return flashinfer.decode.trtllm_batch_decode_with_kv_cache(
-            q,
-            kv_cache,
-            workspace_buffer,
-            num_qo_heads,
-            num_kv_heads,
-            sm_scale,
-            block_tables,
-            kv_lens_tensor,
-            page_size,
-            max_kv_len,
-            kv_cache_dtype,
-            k_scale,
-            v_scale,
-        )
-
-    def time_fn(fn, warmup=10, trials=20):
-        torch.cuda.synchronize()
-        start = torch.cuda.Event(enable_timing=True)
-        end = torch.cuda.Event(enable_timing=True)
-        times = []
-        for i in range(warmup):
-            fn()
-        for i in range(trials):
-            start.record()
-            fn()
-            end.record()
-            torch.cuda.synchronize()
-            times.append(start.elapsed_time(end))  # ms
-        return sum(times) / len(times), torch.std(torch.tensor(times))
-
-    # TRT Decode
-    trt_mean, trt_std = time_fn(trt_decode)
-
-    kv_indptr = [0]
-    kv_indices = []
-    kv_last_page_lens = []
-    for i in range(num_seqs):
-        seq_len = kv_lens[i]
-        assert seq_len > 0
-        num_blocks = (seq_len + page_size - 1) // page_size
-        kv_indices.extend(block_tables[i, :num_blocks])
-        kv_indptr.append(kv_indptr[-1] + num_blocks)
-        kv_last_page_len = seq_len % page_size
-        if kv_last_page_len == 0:
-            kv_last_page_len = page_size
-        kv_last_page_lens.append(kv_last_page_len)
-
-    kv_indptr = torch.tensor(kv_indptr, dtype=torch.int32)
-    kv_indices = torch.tensor(kv_indices, dtype=torch.int32)
-    kv_last_page_lens = torch.tensor(kv_last_page_lens, dtype=torch.int32)
-
-    wrapper = flashinfer.BatchDecodeWithPagedKVCacheWrapper(
-        workspace_buffer,
-        kv_layout,
-        use_tensor_cores=((num_qo_heads // num_kv_heads) > 4),
-    )
-
-    wrapper.plan(
-        kv_indptr,
-        kv_indices,
-        kv_last_page_lens,
-        num_qo_heads,
-        num_kv_heads,
-        head_dim,
-        page_size,
-        "NONE",
-        q_data_type=dtype,
-        kv_data_type=torch.float8_e4m3fn if kv_cache_dtype.startswith("fp8") else dtype,
-    )
-
-    def baseline_decode():
-        return wrapper.run(q, kv_cache, sm_scale, k_scale, v_scale)
-
-    baseline_mean, baseline_std = time_fn(baseline_decode)
-
-    # Calculate percentage speedup (positive means TRT is faster)
-    speedup_percent = (baseline_mean - trt_mean) / baseline_mean
-
-    print(
-        f"\t{num_seqs}\t{max_seq_len}\t{trt_mean:.3f}\t{trt_std.item():.3f}"
-        f"\t{baseline_mean:.3f}\t{baseline_std.item():.3f}\t{speedup_percent:.3f}"
-    )
-
-    # Return results for CSV writing
-    return {
-        "num_seqs": num_seqs,
-        "trt_mean": trt_mean,
-        "trt_std": trt_std.item(),
-        "baseline_mean": baseline_mean,
-        "baseline_std": baseline_std.item(),
-        "speedup_percent": speedup_percent,
-        "q_dtype": str(dtype),
-        "kv_cache_dtype": kv_cache_dtype,
-        "page_size": page_size,
-        "num_kv_heads": num_kv_heads,
-        "head_dim": head_dim,
-        "max_seq_len": max_seq_len,
-    }
-
-
-def write_results_to_csv(results, filename=None):
-    """Write benchmark results to CSV file."""
-    if filename is None:
-        timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
-        filename = f"flashinfer_trtllm_benchmark_{timestamp}.csv"
-
-    fieldnames = [
-        "num_seqs",
-        "trt_mean",
-        "trt_std",
-        "baseline_mean",
-        "baseline_std",
-        "speedup_percent",
-        "q_dtype",
-        "kv_cache_dtype",
-        "page_size",
-        "num_kv_heads",
-        "head_dim",
-        "max_seq_len",
-    ]
-
-    file_exists = os.path.exists(filename)
-
-    with open(filename, "a", newline="") as csvfile:
-        writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
-
-        if not file_exists:
-            writer.writeheader()
-
-        for result in results:
-            writer.writerow(result)
-
-    print(f"Results written to {filename}")
-
-
-if __name__ == "__main__":
-    num_seqs = [1, 4, 8, 16, 32, 64, 128, 256]
-    max_seq_lens = [1024, 2048, 4096, 8192, 16384, 32768, 65536, 131072]
-    all_results = []
-
-    print("Running benchmark for kv_cache_dtype: bfloat16")
-    print(
-        "\tnum_seqs\tmax_seq_len\ttrt_mean\ttrt_std\tbaseline_mean\tbaseline_std\tspeedup_percent"
-    )
-    for max_seq_len in max_seq_lens:
-        for bs in num_seqs:
-            result = benchmark_decode(
-                bs, max_seq_len, dtype=torch.bfloat16, kv_cache_dtype="auto"
-            )
-            all_results.append(result)
-
-    print("Running benchmark for q_dtype = bfloat16, kv_cache_dtype: fp8")
-    print(
-        "\tnum_seqs\tmax_seq_len\ttrt_mean\ttrt_std\tbaseline_mean\tbaseline_std\tspeedup_percent"
-    )
-    for max_seq_len in max_seq_lens:
-        for bs in num_seqs:
-            result = benchmark_decode(
-                bs, max_seq_len, dtype=torch.bfloat16, kv_cache_dtype="fp8"
-            )
-            all_results.append(result)
-
-    # Write all results to CSV
-    write_results_to_csv(all_results)
--- a/benchmarks/kernels/benchmark_trtllm_decode_attention.py
+++ b/benchmarks/kernels/benchmark_trtllm_decode_attention.py
@ -0,0 +1,268 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+import csv
+import os
+from datetime import datetime
+from typing import Optional
+
+import flashinfer
+import torch
+
+FLOAT32_BYTES = torch.finfo(torch.float).bits // 8
+FP8_DTYPE = torch.float8_e4m3fn
+
+
+def to_float8(x, dtype=torch.float8_e4m3fn):
+    finfo = torch.finfo(dtype)
+    min_val, max_val = x.aminmax()
+    amax = torch.maximum(min_val.abs(), max_val.abs()).clamp(min=1e-12)
+    scale = finfo.max / amax * 0.1
+    x_scl_sat = (x * scale).clamp(min=finfo.min, max=finfo.max)
+    return x_scl_sat.to(dtype), scale.float().reciprocal()
+
+
+@torch.no_grad()
+def benchmark_decode(
+    dtype: torch.dtype,
+    quant_dtypes: tuple[
+        Optional[torch.dtype], Optional[torch.dtype], Optional[torch.dtype]
+    ],
+    batch_size: int,
+    max_seq_len: int,
+    num_heads: tuple[int, int] = (64, 8),
+    head_size: int = 128,
+    kv_layout: str = "HND",
+    block_size: int = 16,
+    warmup: int = 10,
+    trials: int = 20,
+):
+    torch.set_default_device("cuda")
+    torch.manual_seed(0)
+
+    q_quant_dtype, kv_quant_dtype, o_quant_dtype = quant_dtypes
+    q_quant_dtype = q_quant_dtype or dtype
+    kv_quant_dtype = kv_quant_dtype or dtype
+    o_quant_dtype = o_quant_dtype or dtype
+
+    num_qo_heads, num_kv_heads = num_heads
+    assert num_qo_heads % num_kv_heads == 0
+
+    sm_scale = float(1.0 / (head_size**0.5))
+
+    # large number to reduce kv_cache reuse
+    NUM_BLOCKS = int(256000 / block_size)
+
+    kv_cache_shape = None
+    if kv_layout == "NHD":
+        kv_cache_shape = (NUM_BLOCKS, 2, block_size, num_kv_heads, head_size)
+    elif kv_layout == "HND":
+        kv_cache_shape = (NUM_BLOCKS, 2, num_kv_heads, block_size, head_size)
+    else:
+        raise ValueError(f"Invalid kv_layout: {kv_layout}")
+
+    query = torch.randn(batch_size, num_qo_heads, head_size, dtype=dtype)
+    if q_quant_dtype == FP8_DTYPE:
+        query, q_scale = to_float8(query)
+        ref_query = query.to(dtype) * q_scale
+    else:
+        q_scale = 1.0
+        ref_query = query
+
+    kv_lens = torch.randint(1, max_seq_len, (batch_size,), dtype=torch.int32)
+    kv_lens[-1] = max_seq_len
+
+    seq_lens = kv_lens
+    max_seq_len = torch.max(seq_lens).item()
+
+    kv_cache = torch.randn(kv_cache_shape, dtype=dtype)
+    if kv_quant_dtype == FP8_DTYPE:
+        kv_cache, kv_scale = to_float8(kv_cache)
+        ref_kv_cache = kv_cache.to(dtype) * kv_scale
+    else:
+        kv_scale = 1.0
+        ref_kv_cache = kv_cache
+    k_scale = v_scale = kv_scale
+
+    max_num_blocks_per_seq = (max_seq_len + block_size - 1) // block_size
+    block_tables = torch.randint(
+        0, NUM_BLOCKS, (batch_size, max_num_blocks_per_seq), dtype=torch.int32
+    )
+    kv_indptr = [0]
+    kv_indices = []
+    kv_last_page_lens = []
+    for i in range(batch_size):
+        seq_len = seq_lens[i]
+        assert seq_len > 0
+        num_blocks = (seq_len + block_size - 1) // block_size
+        kv_indices.extend(block_tables[i, :num_blocks])
+        kv_indptr.append(kv_indptr[-1] + num_blocks)
+        kv_last_page_len = seq_len % block_size
+        if kv_last_page_len == 0:
+            kv_last_page_len = block_size
+        kv_last_page_lens.append(kv_last_page_len)
+
+    kv_indptr = torch.tensor(kv_indptr, dtype=torch.int32)
+    kv_indices = torch.tensor(kv_indices, dtype=torch.int32)
+    kv_last_page_lens = torch.tensor(kv_last_page_lens, dtype=torch.int32)
+    workspace_buffer = torch.zeros(1024 * 1024 * 1024, dtype=torch.int8)
+
+    wrapper = flashinfer.BatchDecodeWithPagedKVCacheWrapper(
+        workspace_buffer,
+        kv_layout,
+        use_tensor_cores=((num_qo_heads // num_kv_heads) > 4),
+    )
+    wrapper.plan(
+        kv_indptr,
+        kv_indices,
+        kv_last_page_lens,
+        num_qo_heads,
+        num_kv_heads,
+        head_size,
+        block_size,
+        "NONE",
+        sm_scale=sm_scale,
+        q_data_type=dtype,
+        kv_data_type=dtype,
+    )
+
+    def time_fn(fn, warmup=10, trials=20):
+        torch.cuda.synchronize()
+        start = torch.cuda.Event(enable_timing=True)
+        end = torch.cuda.Event(enable_timing=True)
+        times = []
+        for i in range(warmup):
+            fn()
+        for i in range(trials):
+            start.record()
+            fn()
+            end.record()
+            torch.cuda.synchronize()
+            times.append(start.elapsed_time(end))  # ms
+        return sum(times) / len(times), torch.std(torch.tensor(times))
+
+    o_scale = 1.0
+    output_baseline = torch.empty(ref_query.shape, dtype=dtype)
+    output_trtllm = torch.empty(query.shape, dtype=o_quant_dtype)
+
+    def baseline_decode():
+        return wrapper.run(ref_query, ref_kv_cache, out=output_baseline)
+
+    def trtllm_decode():
+        return flashinfer.decode.trtllm_batch_decode_with_kv_cache(
+            query=query,
+            kv_cache=kv_cache,
+            workspace_buffer=workspace_buffer,
+            block_tables=block_tables,
+            seq_lens=seq_lens,
+            max_seq_len=max_seq_len,
+            bmm1_scale=q_scale * k_scale * sm_scale,
+            bmm2_scale=v_scale / o_scale,
+            out=output_trtllm,
+        )
+
+    baseline_mean, baseline_std = time_fn(baseline_decode)
+    trtllm_mean, trtllm_std = time_fn(trtllm_decode)
+
+    # Calculate percentage speedup (positive means TRT is faster)
+    speedup_percent = (baseline_mean - trtllm_mean) / baseline_mean
+
+    print(
+        f"\t{batch_size}\t{max_seq_len}\t{trtllm_mean:.3f}\t{trtllm_std.item():.3f}"
+        f"\t{baseline_mean:.3f}\t{baseline_std.item():.3f}\t{speedup_percent:.3f}"
+    )
+
+    # Return results for CSV writing
+    return {
+        "batch_size": batch_size,
+        "trtllm_mean": trtllm_mean,
+        "trtllm_std": trtllm_std.item(),
+        "baseline_mean": baseline_mean,
+        "baseline_std": baseline_std.item(),
+        "speedup_percent": speedup_percent,
+        "q_dtype": str(q_quant_dtype),
+        "kv_cache_dtype": str(kv_quant_dtype),
+        "output_dtype": str(o_quant_dtype),
+        "block_size": block_size,
+        "num_kv_heads": num_kv_heads,
+        "head_size": head_size,
+        "max_seq_len": max_seq_len,
+    }
+
+
+def write_results_to_csv(results, filename=None):
+    """Write benchmark results to CSV file."""
+    if filename is None:
+        timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+        filename = f"flashinfer_trtllm_benchmark_{timestamp}.csv"
+
+    fieldnames = [
+        "batch_size",
+        "trtllm_mean",
+        "trtllm_std",
+        "baseline_mean",
+        "baseline_std",
+        "speedup_percent",
+        "q_dtype",
+        "kv_cache_dtype",
+        "output_dtype",
+        "block_size",
+        "num_kv_heads",
+        "head_size",
+        "max_seq_len",
+    ]
+
+    file_exists = os.path.exists(filename)
+
+    with open(filename, "a", newline="") as csvfile:
+        writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
+
+        if not file_exists:
+            writer.writeheader()
+
+        for result in results:
+            writer.writerow(result)
+
+    print(f"Results written to {filename}")
+
+
+if __name__ == "__main__":
+    batch_sizes = [1, 4, 8, 16, 32, 64, 128, 256]
+    max_seq_lens = [1024, 2048, 4096, 8192, 16384, 32768, 65536, 131072]
+    all_results = []
+
+    dtype = torch.bfloat16
+    quant_dtypes = [
+        # (q_quant_dtype, kv_quant_dtype, o_quant_dtype)
+        (None, None, None),
+        (None, FP8_DTYPE, None),
+        (FP8_DTYPE, FP8_DTYPE, FP8_DTYPE),
+    ]
+
+    for quant_dtype in quant_dtypes:
+        q_quant_dtype, kv_quant_dtype, o_quant_dtype = quant_dtype
+        q_quant_dtype = q_quant_dtype or dtype
+        kv_quant_dtype = kv_quant_dtype or dtype
+        o_quant_dtype = o_quant_dtype or dtype
+
+        print(
+            f"Running benchmark for q_dtype = {q_quant_dtype}, "
+            f"kv_cache_dtype: {kv_quant_dtype}, "
+            f"output_dtype: {o_quant_dtype}"
+        )
+        print(
+            "\tbatch_size\tmax_seq_len\ttrtllm_mean\ttrtllm_std\tbaseline_mean\t"
+            "baseline_std\tspeedup_percent"
+        )
+        for max_seq_len in max_seq_lens:
+            for bs in batch_sizes:
+                result = benchmark_decode(
+                    dtype=dtype,
+                    quant_dtypes=quant_dtype,
+                    batch_size=bs,
+                    max_seq_len=max_seq_len,
+                )
+                all_results.append(result)
+
+    # Write all results to CSV
+    write_results_to_csv(all_results)
--- a/benchmarks/kernels/benchmark_trtllm_prefill_attention.py
+++ b/benchmarks/kernels/benchmark_trtllm_prefill_attention.py
@ -0,0 +1,281 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+import csv
+import os
+from datetime import datetime
+from typing import Optional
+
+import flashinfer
+import torch
+
+FLOAT32_BYTES = torch.finfo(torch.float).bits // 8
+FP8_DTYPE = torch.float8_e4m3fn
+
+
+def to_float8(x, dtype=torch.float8_e4m3fn):
+    finfo = torch.finfo(dtype)
+    min_val, max_val = x.aminmax()
+    amax = torch.maximum(min_val.abs(), max_val.abs()).clamp(min=1e-12)
+    scale = finfo.max / amax * 0.1
+    x_scl_sat = (x * scale).clamp(min=finfo.min, max=finfo.max)
+    return x_scl_sat.to(dtype), scale.float().reciprocal()
+
+
+@torch.no_grad()
+def benchmark_prefill(
+    dtype: torch.dtype,
+    quant_dtypes: tuple[
+        Optional[torch.dtype], Optional[torch.dtype], Optional[torch.dtype]
+    ],
+    batch_size: int,
+    max_seq_len: int,
+    num_heads: tuple[int, int] = (64, 8),
+    head_size: int = 128,
+    kv_layout: str = "HND",
+    block_size: int = 16,
+    warmup: int = 10,
+    trials: int = 20,
+):
+    torch.set_default_device("cuda")
+    torch.manual_seed(0)
+
+    q_quant_dtype, kv_quant_dtype, o_quant_dtype = quant_dtypes
+    q_quant_dtype = q_quant_dtype or dtype
+    kv_quant_dtype = kv_quant_dtype or dtype
+    o_quant_dtype = o_quant_dtype or dtype
+
+    max_q_len = max_kv_len = max_seq_len
+
+    num_qo_heads, num_kv_heads = num_heads
+    assert num_qo_heads % num_kv_heads == 0
+
+    sm_scale = float(1.0 / (head_size**0.5))
+
+    # large number to reduce kv_cache reuse
+    NUM_BLOCKS = int(256000 / block_size)
+
+    kv_cache_shape = None
+    if kv_layout == "NHD":
+        kv_cache_shape = (NUM_BLOCKS, 2, block_size, num_kv_heads, head_size)
+    elif kv_layout == "HND":
+        kv_cache_shape = (NUM_BLOCKS, 2, num_kv_heads, block_size, head_size)
+    else:
+        raise ValueError(f"Invalid kv_layout: {kv_layout}")
+
+    q_lens = torch.randint(1, max_q_len, (batch_size,), dtype=torch.int32)
+    q_lens[-1] = max_q_len
+    q_indptr = torch.cat(
+        [
+            torch.tensor([0], dtype=torch.int32),
+            torch.cumsum(q_lens, dim=0, dtype=torch.int32),
+        ]
+    )
+
+    query = torch.randn(torch.sum(q_lens).item(), num_qo_heads, head_size, dtype=dtype)
+    if q_quant_dtype == FP8_DTYPE:
+        query, q_scale = to_float8(query)
+        ref_query = query.to(dtype) * q_scale
+    else:
+        q_scale = 1.0
+        ref_query = query
+
+    kv_lens = torch.randint(0, max_kv_len, (batch_size,), dtype=torch.int32)
+    kv_lens[-1] = max_kv_len
+
+    seq_lens = kv_lens + q_lens
+    max_seq_len = torch.max(seq_lens).item()
+
+    kv_cache = torch.randn(kv_cache_shape, dtype=dtype)
+    if kv_quant_dtype == FP8_DTYPE:
+        kv_cache, kv_scale = to_float8(kv_cache)
+        ref_kv_cache = kv_cache.to(dtype) * kv_scale
+    else:
+        kv_scale = 1.0
+        ref_kv_cache = kv_cache
+    k_scale = v_scale = kv_scale
+
+    max_num_blocks_per_seq = (max_seq_len + block_size - 1) // block_size
+    block_tables = torch.randint(
+        0, NUM_BLOCKS, (batch_size, max_num_blocks_per_seq), dtype=torch.int32
+    )
+    kv_indptr = [0]
+    kv_indices = []
+    kv_last_page_lens = []
+    for i in range(batch_size):
+        seq_len = seq_lens[i]
+        assert seq_len > 0
+        num_blocks = (seq_len + block_size - 1) // block_size
+        kv_indices.extend(block_tables[i, :num_blocks])
+        kv_indptr.append(kv_indptr[-1] + num_blocks)
+        kv_last_page_len = seq_len % block_size
+        if kv_last_page_len == 0:
+            kv_last_page_len = block_size
+        kv_last_page_lens.append(kv_last_page_len)
+
+    kv_indptr = torch.tensor(kv_indptr, dtype=torch.int32)
+    kv_indices = torch.tensor(kv_indices, dtype=torch.int32)
+    kv_last_page_lens = torch.tensor(kv_last_page_lens, dtype=torch.int32)
+    workspace_buffer = torch.zeros(1024 * 1024 * 1024, dtype=torch.int8)
+
+    wrapper = flashinfer.BatchPrefillWithPagedKVCacheWrapper(
+        workspace_buffer, kv_layout
+    )
+    wrapper.plan(
+        q_indptr,
+        kv_indptr,
+        kv_indices,
+        kv_last_page_lens,
+        num_qo_heads,
+        num_kv_heads,
+        head_size,
+        block_size,
+        causal=True,
+        sm_scale=sm_scale,
+        q_data_type=dtype,
+        kv_data_type=dtype,
+    )
+
+    def time_fn(fn, warmup=10, trials=20):
+        torch.cuda.synchronize()
+        start = torch.cuda.Event(enable_timing=True)
+        end = torch.cuda.Event(enable_timing=True)
+        times = []
+        for i in range(warmup):
+            fn()
+        for i in range(trials):
+            start.record()
+            fn()
+            end.record()
+            torch.cuda.synchronize()
+            times.append(start.elapsed_time(end))  # ms
+        return sum(times) / len(times), torch.std(torch.tensor(times))
+
+    o_scale = 1.0
+    output_baseline = torch.empty(ref_query.shape, dtype=dtype)
+    output_trtllm = torch.empty(query.shape, dtype=o_quant_dtype)
+
+    def baseline_prefill():
+        return wrapper.run(ref_query, ref_kv_cache, out=output_baseline)
+
+    def trtllm_prefill():
+        return flashinfer.prefill.trtllm_batch_context_with_kv_cache(
+            query=query,
+            kv_cache=kv_cache,
+            workspace_buffer=workspace_buffer,
+            block_tables=block_tables,
+            seq_lens=seq_lens,
+            max_q_len=max_q_len,
+            max_kv_len=max_seq_len,
+            bmm1_scale=q_scale * k_scale * sm_scale,
+            bmm2_scale=v_scale / o_scale,
+            batch_size=batch_size,
+            cum_seq_lens_q=q_indptr,
+            cum_seq_lens_kv=kv_indptr,
+            out=output_trtllm,
+        )
+
+    baseline_mean, baseline_std = time_fn(baseline_prefill)
+    trtllm_mean, trtllm_std = time_fn(trtllm_prefill)
+
+    # Calculate percentage speedup (positive means TRT is faster)
+    speedup_percent = (baseline_mean - trtllm_mean) / baseline_mean
+
+    print(
+        f"\t{batch_size}\t{max_seq_len}\t{trtllm_mean:8.3f}\t{trtllm_std.item():8.3f}"
+        f"\t{baseline_mean:8.3f}\t{baseline_std.item():8.3f}\t{speedup_percent:8.3f}"
+    )
+
+    # Return results for CSV writing
+    return {
+        "batch_size": batch_size,
+        "trtllm_mean": trtllm_mean,
+        "trtllm_std": trtllm_std.item(),
+        "baseline_mean": baseline_mean,
+        "baseline_std": baseline_std.item(),
+        "speedup_percent": speedup_percent,
+        "q_dtype": str(q_quant_dtype),
+        "kv_cache_dtype": str(kv_quant_dtype),
+        "output_dtype": str(o_quant_dtype),
+        "block_size": block_size,
+        "num_kv_heads": num_kv_heads,
+        "head_size": head_size,
+        "max_seq_len": max_seq_len,
+    }
+
+
+def write_results_to_csv(results, filename=None):
+    """Write benchmark results to CSV file."""
+    if filename is None:
+        timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+        filename = f"flashinfer_trtllm_benchmark_{timestamp}.csv"
+
+    fieldnames = [
+        "batch_size",
+        "trtllm_mean",
+        "trtllm_std",
+        "baseline_mean",
+        "baseline_std",
+        "speedup_percent",
+        "q_dtype",
+        "kv_cache_dtype",
+        "output_dtype",
+        "block_size",
+        "num_kv_heads",
+        "head_size",
+        "max_seq_len",
+    ]
+
+    file_exists = os.path.exists(filename)
+
+    with open(filename, "a", newline="") as csvfile:
+        writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
+
+        if not file_exists:
+            writer.writeheader()
+
+        for result in results:
+            writer.writerow(result)
+
+    print(f"Results written to {filename}")
+
+
+if __name__ == "__main__":
+    batch_sizes = [1, 4, 8, 16, 32, 64, 128, 256]
+    max_seq_lens = [1024, 2048, 4096, 8192, 16384, 32768, 65536, 131072]
+    all_results = []
+
+    dtype = torch.bfloat16
+    quant_dtypes = [
+        # (q_quant_dtype, kv_quant_dtype, o_quant_dtype)
+        (None, None, None),
+        (FP8_DTYPE, FP8_DTYPE, FP8_DTYPE),
+    ]
+
+    for quant_dtype in quant_dtypes:
+        q_quant_dtype, kv_quant_dtype, o_quant_dtype = quant_dtype
+        q_quant_dtype = q_quant_dtype or dtype
+        kv_quant_dtype = kv_quant_dtype or dtype
+        o_quant_dtype = o_quant_dtype or dtype
+
+        print(
+            f"Running benchmark for q_dtype = {q_quant_dtype}, "
+            f"kv_cache_dtype: {kv_quant_dtype}, "
+            f"output_dtype: {o_quant_dtype}"
+        )
+        print(
+            "\tbatch_size\tmax_seq_len\ttrtllm_mean\ttrtllm_std\tbaseline_mean\t"
+            "baseline_std\tspeedup_percent"
+        )
+        for max_seq_len in max_seq_lens:
+            for bs in batch_sizes:
+                result = benchmark_prefill(
+                    dtype=dtype,
+                    quant_dtypes=quant_dtype,
+                    batch_size=bs,
+                    max_seq_len=max_seq_len,
+                )
+                all_results.append(result)
+
+    # Write all results to CSV
+    write_results_to_csv(all_results)
--- a/benchmarks/kernels/deepgemm/README.md
+++ b/benchmarks/kernels/deepgemm/README.md
@ -8,7 +8,7 @@ Currently this just includes dense GEMMs and only works on Hopper GPUs.

 You need to install vLLM in your usual fashion, then install DeepGEMM from source in its own directory:

-```
+```bash
 git clone --recursive https://github.com/deepseek-ai/DeepGEMM
 cd DeepGEMM
 python setup.py install
@ -17,7 +17,7 @@ uv pip install -e .

 ## Usage

-```
+```console
 python benchmark_fp8_block_dense_gemm.py
 INFO 02-26 21:55:13 [__init__.py:207] Automatically detected platform cuda.
 ===== STARTING FP8 GEMM BENCHMARK =====
--- a/benchmarks/kernels/deepgemm/benchmark_fp8_block_dense_gemm.py
+++ b/benchmarks/kernels/deepgemm/benchmark_fp8_block_dense_gemm.py
@ -4,49 +4,16 @@
 # ruff: noqa: E501
 import time

-# Import DeepGEMM functions
-import deep_gemm
 import torch
-from deep_gemm import calc_diff, ceil_div, get_col_major_tma_aligned_tensor

-# Import vLLM functions
 from vllm import _custom_ops as ops
 from vllm.model_executor.layers.quantization.utils.fp8_utils import (
+    get_col_major_tma_aligned_tensor,
    per_token_group_quant_fp8,
    w8a8_block_fp8_matmul,
 )
 from vllm.triton_utils import triton
-
-
-# Copied from
-# https://github.com/deepseek-ai/DeepGEMM/blob/78cacf70d41d15d688bd493ebc85845f7f2a3d5d/tests/test_core.py#L9
-def per_token_cast_to_fp8(
-        x: torch.Tensor) -> tuple[torch.Tensor, torch.Tensor]:
-    """Convert tensor to FP8 format with per-token scaling."""
-    assert x.dim() == 2 and x.size(1) % 128 == 0
-    m, n = x.shape
-    x_view = x.view(m, -1, 128)
-    x_amax = x_view.abs().float().amax(dim=2).view(m, -1).clamp(1e-4)
-    return (x_view * (448.0 / x_amax.unsqueeze(2))).to(
-        torch.float8_e4m3fn).view(m, n), (x_amax / 448.0).view(m, -1)
-
-
-# Copied from
-# https://github.com/deepseek-ai/DeepGEMM/blob/78cacf70d41d15d688bd493ebc85845f7f2a3d5d/tests/test_core.py#L17
-def per_block_cast_to_fp8(
-        x: torch.Tensor) -> tuple[torch.Tensor, torch.Tensor]:
-    """Convert tensor to FP8 format with per-block scaling."""
-    assert x.dim() == 2
-    m, n = x.shape
-    x_padded = torch.zeros((ceil_div(m, 128) * 128, ceil_div(n, 128) * 128),
-                           dtype=x.dtype,
-                           device=x.device)
-    x_padded[:m, :n] = x
-    x_view = x_padded.view(-1, 128, x_padded.size(1) // 128, 128)
-    x_amax = x_view.abs().float().amax(dim=(1, 3), keepdim=True).clamp(1e-4)
-    x_scaled = (x_view * (448.0 / x_amax)).to(torch.float8_e4m3fn)
-    return x_scaled.view_as(x_padded)[:m, :n].contiguous(), (
-        x_amax / 448.0).view(x_view.size(0), x_view.size(2))
+from vllm.utils.deep_gemm import calc_diff, fp8_gemm_nt, per_block_cast_to_fp8


 def benchmark_shape(m: int,
@ -69,14 +36,14 @@ def benchmark_shape(m: int,

    # Pre-quantize B for all implementations
    # (weights can be pre-quantized offline)
-    B_deepgemm, B_scale_deepgemm = per_block_cast_to_fp8(B)
-    B_vllm, B_scale_vllm = per_block_cast_to_fp8(B)
+    B_deepgemm, B_scale_deepgemm = per_block_cast_to_fp8(B, [128, 128], use_ue8m0=True)
+    B_vllm, B_scale_vllm = per_block_cast_to_fp8(B, [128, 128], use_ue8m0=True)

    # Block size configuration
    block_size = [128, 128]

    # Pre-quantize A for all implementations
-    A_deepgemm, A_scale_deepgemm = per_token_cast_to_fp8(A)
+    A_deepgemm, A_scale_deepgemm = per_token_group_quant_fp8(A, block_size[1])
    A_scale_deepgemm = get_col_major_tma_aligned_tensor(A_scale_deepgemm)
    C_deepgemm = torch.empty((m, n), device='cuda', dtype=torch.bfloat16)
    A_vllm, A_scale_vllm = per_token_group_quant_fp8(A, block_size[1])
@ -85,7 +52,7 @@ def benchmark_shape(m: int,

    # === DeepGEMM Implementation ===
    def deepgemm_gemm():
-        deep_gemm.gemm_fp8_fp8_bf16_nt((A_deepgemm, A_scale_deepgemm),
+        fp8_gemm_nt((A_deepgemm, A_scale_deepgemm),
                                       (B_deepgemm, B_scale_deepgemm),
                                       C_deepgemm)
        return C_deepgemm
--- a/benchmarks/kv_cache/benchmark_block_pool.py
+++ b/benchmarks/kv_cache/benchmark_block_pool.py
@ -1,108 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-import gc
-import time
-from typing import Optional
-
-from tabulate import tabulate
-
-from vllm.utils import FlexibleArgumentParser
-from vllm.v1.core.block_pool import BlockPool
-
-
-class Metric:
-    def __init__(self) -> None:
-        self.cnt: int = 0
-        self.sum_v: int = 0
-        self.max_v: Optional[int] = None
-
-    def update(self, v: int) -> None:
-        self.cnt += 1
-        self.sum_v += v
-        if self.max_v is None:
-            self.max_v = v
-        else:
-            self.max_v = max(self.max_v, v)
-
-    def avg_v(self) -> float:
-        return self.sum_v * 1.0 / self.cnt
-
-
-def main(args):
-    rows = []
-    for allocate_block in args.allocate_blocks:
-        # Enforce a GC collect ahead to minimize the impact among runs
-        gc.collect()
-        block_pool = BlockPool(num_gpu_blocks=args.num_gpu_blocks, enable_caching=True)
-
-        get_blocks_metric: Metric = Metric()
-        free_blocks_metric: Metric = Metric()
-        for _ in range(args.num_iteration):
-            t1 = time.monotonic_ns()
-            blocks = block_pool.get_new_blocks(allocate_block)
-            t2 = time.monotonic_ns()
-            block_pool.free_blocks(blocks)
-            t3 = time.monotonic_ns()
-            get_blocks_metric.update(t2 - t1)
-            free_blocks_metric.update(t3 - t2)
-
-        if get_blocks_metric.max_v is not None and free_blocks_metric.max_v is not None:
-            rows.append(
-                [
-                    get_blocks_metric.cnt,
-                    args.num_gpu_blocks,
-                    allocate_block,
-                    get_blocks_metric.avg_v() / 1000000,
-                    get_blocks_metric.max_v / 1000000.0,
-                    free_blocks_metric.avg_v() / 1000000,
-                    free_blocks_metric.max_v / 1000000.0,
-                ]
-            )
-        else:
-            print(
-                "No valid metrics found."
-                f" {get_blocks_metric.max_v=} {free_blocks_metric.max_v=}"
-            )
-
-    print(
-        tabulate(
-            rows,
-            headers=[
-                "Iterations",
-                "Total\nBlocks",
-                "Allocated\nBlocks",
-                "Get Blocks\nAvg (ms)",
-                "Get Blocks\nMax (ms)",
-                "Free Blocks\nAvg (ms)",
-                "Free Blocks\nMax (ms)",
-            ],
-            tablefmt="grid",
-            floatfmt=".6f",
-        )
-    )
-
-
-def invoke_main() -> None:
-    parser = FlexibleArgumentParser(
-        description="Benchmark the performance of BlockPool for KV Cache."
-    )
-    parser.add_argument("--num-gpu-blocks", type=int, default=100000)
-    parser.add_argument(
-        "--num-iteration",
-        type=int,
-        default=1000,
-        help="Number of iterations to run to stablize final data readings",
-    )
-    parser.add_argument(
-        "--allocate-blocks",
-        type=int,
-        nargs="*",
-        default=[10, 50, 100, 500, 1000],
-        help="Number of blocks to allocate",
-    )
-    args = parser.parse_args()
-    main(args)
-
-
-if __name__ == "__main__":
-    invoke_main()  # pragma: no cover
--- a/benchmarks/multi_turn/README.md
+++ b/benchmarks/multi_turn/README.md
@ -0,0 +1,73 @@
+# Benchmark KV Cache Offloading with Multi-Turn Conversations
+
+The requirements (pip) for `benchmark_serving_multi_turn.py` can be found in `requirements.txt`
+
+First start serving your model
+
+```bash
+export MODEL_PATH=/models/meta-llama/Meta-Llama-3.1-8B-Instruct/
+
+vllm serve $MODEL_PATH --served-model-name Llama --disable-log-requests
+```
+
+The variable `MODEL_PATH` should be a path to the model files (e.g. downloaded from huggingface).
+
+## Synthetic Multi-Turn Conversations
+
+Download the following text file (used for generation of synthetic conversations)
+
+```bash
+wget https://www.gutenberg.org/ebooks/1184.txt.utf-8
+mv 1184.txt.utf-8 pg1184.txt
+```
+
+The filename `pg1184.txt` is used in `generate_multi_turn.json` (see `"text_files"`).
+
+But you may use other text files if you prefer (using this specific file is not required).
+
+Then run the benchmarking script
+
+```bash
+export MODEL_PATH=/models/meta-llama/Meta-Llama-3.1-8B-Instruct/
+
+python benchmark_serving_multi_turn.py --model $MODEL_PATH --served-model-name Llama \
+--input-file generate_multi_turn.json --num-clients 2 --max-active-conversations 6
+```
+
+You can edit the file `generate_multi_turn.json` to change the conversation parameters (number of turns, etc.).
+
+If successful, you will see the following output
+
+```bash
+----------------------------------------------------------------------------------------------------
+Statistics summary:
+runtime_sec = 215.810
+requests_per_sec = 0.769
+----------------------------------------------------------------------------------------------------
+                   count     mean     std      min      25%      50%      75%      90%      99%      max
+ttft_ms            166.0    78.22   67.63    45.91    59.94    62.26    64.43    69.66   353.18   567.54
+tpot_ms            166.0    25.37    0.57    24.40    25.07    25.31    25.50    25.84    27.50    28.05
+latency_ms         166.0  2591.07  326.90  1998.53  2341.62  2573.01  2860.10  3003.50  3268.46  3862.94
+input_num_turns    166.0     7.43    4.57     1.00     3.00     7.00    11.00    13.00    17.00    17.00
+input_num_tokens   166.0  2006.20  893.56   522.00  1247.75  2019.00  2718.00  3233.00  3736.45  3899.00
+output_num_tokens  166.0   100.01   11.80    80.00    91.00    99.00   109.75   116.00   120.00   120.00
+output_num_chunks  166.0    99.01   11.80    79.00    90.00    98.00   108.75   115.00   119.00   119.00
+----------------------------------------------------------------------------------------------------
+```
+
+## ShareGPT Conversations
+
+To run with the ShareGPT data, download the following ShareGPT dataset:
+`https://huggingface.co/datasets/philschmid/sharegpt-raw/blob/main/sharegpt_20230401_clean_lang_split.json`
+
+Use the `convert_sharegpt_to_openai.py` script to convert the dataset to a format supported by `benchmark_serving_multi_turn.py`
+
+```bash
+python convert_sharegpt_to_openai.py sharegpt_20230401_clean_lang_split.json sharegpt_conv_128.json --seed=99 --max-items=128
+```
+
+The script will convert the ShareGPT dataset to a dataset with the standard user/assistant roles.
+
+The flag `--max-items=128` is used to sample 128 conversations from the original dataset (change as needed).
+
+Use the output JSON file `sharegpt_conv_128.json` as the `--input-file` for `benchmark_serving_multi_turn.py`.
--- a/benchmarks/multi_turn/bench_dataset.py
+++ b/benchmarks/multi_turn/bench_dataset.py
@ -0,0 +1,493 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+from abc import ABC, abstractmethod
+from statistics import mean
+from typing import Any, NamedTuple, Optional, Union
+
+import numpy as np  # type: ignore
+import pandas as pd  # type: ignore
+from bench_utils import (
+    TEXT_SEPARATOR,
+    Color,
+    logger,
+)
+from transformers import AutoTokenizer  # type: ignore
+
+# Conversation ID is a string (e.g: "UzTK34D")
+ConvId = str
+
+# A list of dicts (dicts with keys "id" and "messages")
+ShareGptConversations = list[dict[str, Any]]
+
+# A list of dicts (dicts with keys "role" and "content")
+MessagesList = list[dict[str, str]]
+
+# Map conversation ID to conversation messages
+ConversationsMap = list[ConvId, MessagesList]
+
+
+class Distribution(ABC):
+    @abstractmethod
+    def sample(self, size: int = 1) -> np.ndarray:
+        pass
+
+
+class UniformDistribution(Distribution):
+    def __init__(
+        self,
+        min_val: Union[int, float],
+        max_val: Union[int, float],
+        is_integer: bool = True,
+    ) -> None:
+        self.min_val = min_val
+        self.max_val = max_val
+        self.is_integer = is_integer
+
+    def sample(self, size: int = 1) -> np.ndarray:
+        if self.is_integer:
+            return np.random.randint(
+                int(self.min_val), int(self.max_val + 1), size=size
+            )
+        else:
+            return np.random.uniform(self.min_val, self.max_val, size=size)
+
+    def __repr__(self) -> str:
+        return f"UniformDistribution[{self.min_val}, {self.max_val}]"
+
+
+class ConstantDistribution(Distribution):
+    def __init__(self, value: Union[int, float]) -> None:
+        self.value = value
+        self.max_val = value
+
+    def sample(self, size: int = 1) -> np.ndarray:
+        return np.full(shape=size, fill_value=self.value)
+
+    def __repr__(self) -> str:
+        return f"Constant[{self.value}]"
+
+
+class ZipfDistribution(Distribution):
+    def __init__(self, alpha: float, max_val: Optional[int] = None) -> None:
+        self.alpha = alpha
+        self.max_val = max_val
+
+    def sample(self, size: int = 1) -> np.ndarray:
+        samples = np.random.zipf(self.alpha, size=size)
+        if self.max_val:
+            samples = np.minimum(samples, self.max_val)
+        return samples
+
+    def __repr__(self) -> str:
+        return f"ZipfDistribution[{self.alpha}]"
+
+
+class PoissonDistribution(Distribution):
+    def __init__(self, alpha: float, max_val: Optional[int] = None) -> None:
+        self.alpha = alpha
+        self.max_val = max_val
+
+    def sample(self, size: int = 1) -> np.ndarray:
+        samples = np.random.poisson(self.alpha, size=size)
+        if self.max_val:
+            samples = np.minimum(samples, self.max_val)
+        return samples
+
+    def __repr__(self) -> str:
+        return f"PoissonDistribution[{self.alpha}]"
+
+
+class LognormalDistribution(Distribution):
+    def __init__(
+        self, mean: float, sigma: float, max_val: Optional[int] = None
+    ) -> None:
+        self.mean = mean
+        self.sigma = sigma
+        self.max_val = max_val
+
+    def sample(self, size: int = 1) -> np.ndarray:
+        samples = np.random.lognormal(mean=self.mean, sigma=self.sigma, size=size)
+        if self.max_val:
+            samples = np.minimum(samples, self.max_val)
+
+        return np.round(samples).astype(int)
+
+    def __repr__(self) -> str:
+        return f"LognormalDistribution[{self.mean}, {self.sigma}]"
+
+
+class GenConvArgs(NamedTuple):
+    num_conversations: int
+    text_files: list[str]
+    input_num_turns: Distribution
+    input_common_prefix_num_tokens: Distribution
+    input_prefix_num_tokens: Distribution
+    input_num_tokens: Distribution
+    output_num_tokens: Distribution
+    print_stats: bool
+
+
+def verify_field_exists(
+    conf: dict, field_name: str, section: str, subsection: str
+) -> None:
+    if field_name not in conf:
+        raise ValueError(
+            f"Missing field '{field_name}' in {section=} and {subsection=}"
+        )
+
+
+def get_random_distribution(
+    conf: dict, section: str, subsection: str, optional: bool = False
+) -> Distribution:
+    # section can be "prompt_input" or "prompt_output" (both required)
+    conf = conf[section]
+
+    if optional and subsection not in conf:
+        # Optional subsection, if not found assume the value is always 0
+        return ConstantDistribution(0)
+
+    # subsection can be "num_turns", "num_tokens" or "prefix_num_tokens"
+    if subsection not in conf:
+        raise ValueError(f"Missing subsection {subsection} in section {section}")
+
+    conf = conf[subsection]
+
+    distribution = conf.get("distribution")
+    if distribution is None:
+        raise ValueError(
+            f"Missing field 'distribution' in {section=} and {subsection=}"
+        )
+
+    if distribution == "constant":
+        verify_field_exists(conf, "value", section, subsection)
+        return ConstantDistribution(conf["value"])
+
+    elif distribution == "zipf":
+        verify_field_exists(conf, "alpha", section, subsection)
+        max_val = conf.get("max", None)
+        return ZipfDistribution(conf["alpha"], max_val=max_val)
+
+    elif distribution == "poisson":
+        verify_field_exists(conf, "alpha", section, subsection)
+        max_val = conf.get("max", None)
+        return PoissonDistribution(conf["alpha"], max_val=max_val)
+
+    elif distribution == "lognormal":
+        verify_field_exists(conf, "mean", section, subsection)
+        verify_field_exists(conf, "sigma", section, subsection)
+        max_val = conf.get("max", None)
+        return LognormalDistribution(conf["mean"], conf["sigma"], max_val=max_val)
+
+    elif distribution == "uniform":
+        verify_field_exists(conf, "min", section, subsection)
+        verify_field_exists(conf, "max", section, subsection)
+
+        min_value = conf["min"]
+        max_value = conf["max"]
+
+        assert min_value > 0
+        assert min_value <= max_value
+
+        is_integer = isinstance(min_value, int) and isinstance(max_value, int)
+        return UniformDistribution(min_value, max_value, is_integer)
+    else:
+        raise ValueError(f"Unknown distribution: {distribution}")
+
+
+def parse_input_json_file(conf: dict) -> GenConvArgs:
+    # Validate the input file
+    assert isinstance(conf, dict)
+    required_fields = [
+        "filetype",
+        "num_conversations",
+        "text_files",
+        "prompt_input",
+        "prompt_output",
+    ]
+    for field in required_fields:
+        assert field in conf, f"Missing field {field} in input {conf}"
+
+    assert conf["filetype"] == "generate_conversations"
+
+    assert conf["num_conversations"] > 0, "num_conversations should be larger than zero"
+
+    text_files = conf["text_files"]
+
+    assert isinstance(text_files, list), "Field 'text_files' should be a list"
+    assert len(text_files) > 0, (
+        "Field 'text_files' should be a list with at least one file"
+    )
+
+    # Parse the parameters for the prompt input/output workload
+    input_num_turns = get_random_distribution(conf, "prompt_input", "num_turns")
+    input_num_tokens = get_random_distribution(conf, "prompt_input", "num_tokens")
+    input_common_prefix_num_tokens = get_random_distribution(
+        conf, "prompt_input", "common_prefix_num_tokens", optional=True
+    )
+    input_prefix_num_tokens = get_random_distribution(
+        conf, "prompt_input", "prefix_num_tokens"
+    )
+    output_num_tokens = get_random_distribution(conf, "prompt_output", "num_tokens")
+
+    print_stats: bool = conf.get("print_stats", False)
+    assert isinstance(print_stats, bool), (
+        "Field 'print_stats' should be either 'true' or 'false'"
+    )
+
+    args = GenConvArgs(
+        num_conversations=conf["num_conversations"],
+        text_files=text_files,
+        input_num_turns=input_num_turns,
+        input_common_prefix_num_tokens=input_common_prefix_num_tokens,
+        input_prefix_num_tokens=input_prefix_num_tokens,
+        input_num_tokens=input_num_tokens,
+        output_num_tokens=output_num_tokens,
+        print_stats=print_stats,
+    )
+    return args
+
+
+def print_conv_stats(conversations: ConversationsMap, tokenizer: AutoTokenizer) -> None:
+    # Collect statistics
+    conv_stats: list[dict[Any, Any]] = []
+    req_stats: list[int] = []
+
+    print("\nCollecting statistics...")
+    for messages in conversations.values():
+        # messages is a list of dicts
+        user_tokens: list[int] = []
+        assistant_tokens: list[int] = []
+        request_tokens: list[int] = []
+
+        req_tokens = 0
+        for m in messages:
+            content = m["content"]
+            num_tokens = len(tokenizer(content).input_ids)
+
+            if m["role"] == "user":
+                user_tokens.append(num_tokens)
+                # New user prompt including all chat history
+                req_tokens += num_tokens
+                request_tokens.append(req_tokens)
+
+            elif m["role"] == "assistant":
+                assistant_tokens.append(num_tokens)
+                # Update assistant answer
+                # (will be part of chat history for the next user prompt)
+                req_tokens += num_tokens
+
+        item_stats = {
+            "conversation_turns": len(messages),
+            "user_tokens": mean(user_tokens),
+            "assistant_tokens": mean(assistant_tokens),
+        }
+
+        conv_stats.append(item_stats)
+        req_stats.extend(request_tokens)
+
+    # Print statistics
+    percentiles = [0.25, 0.5, 0.75, 0.9, 0.99]
+
+    print(TEXT_SEPARATOR)
+    print(f"{Color.YELLOW}Conversations statistics:{Color.RESET}")
+    print(TEXT_SEPARATOR)
+    df = pd.DataFrame(conv_stats)
+    print(df.describe(percentiles=percentiles).transpose())
+    print(TEXT_SEPARATOR)
+    print(f"{Color.YELLOW}Request statistics:{Color.RESET}")
+    print(TEXT_SEPARATOR)
+    df = pd.DataFrame(req_stats, columns=["request_tokens"])
+    print(df.describe(percentiles=percentiles).transpose())
+    print(TEXT_SEPARATOR)
+
+
+def generate_conversations(
+    args: GenConvArgs, tokenizer: AutoTokenizer
+) -> ConversationsMap:
+    # Text for all user prompts
+    # (text from the input text files will be appended to this line)
+    base_prompt_text = "Please rewrite the following text and add more content: "
+    base_prompt_token_count = len(
+        tokenizer.encode(base_prompt_text, add_special_tokens=False)
+    )
+
+    logger.info(f"{Color.PURPLE}Generating conversations...{Color.RESET}")
+    logger.info(args)
+
+    list_of_tokens = []
+
+    for filename in args.text_files:
+        # Load text file that will be used to generate prompts
+        with open(filename) as file:
+            data = file.read()
+            tokens_in_file = tokenizer.encode(data, add_special_tokens=False)
+            list_of_tokens.extend(tokens_in_file)
+
+    conversations: ConversationsMap = {}
+    conv_id = 0
+
+    # Generate number of turns for every conversation
+    turn_count: np.ndarray = args.input_num_turns.sample(args.num_conversations)
+
+    # Turn count should be at least 2 (one user prompt and one assistant answer)
+    turn_count = np.maximum(turn_count, 2)
+
+    # Round up to an even number (every user prompt should have an answer)
+    turn_count = turn_count + (turn_count % 2)
+
+    # Generate number of prefix tokens for every conversation
+    conv_prefix_tokens: np.ndarray = args.input_prefix_num_tokens.sample(
+        args.num_conversations
+    )
+
+    # Used to reduce shared text between conversations
+    # (jump/skip over text sections between conversations)
+    base_offset = 0
+
+    # Common prefix size for all conversations (only 1 sample required)
+    common_prefix_text = ""
+    common_prefix_tokens: int = args.input_common_prefix_num_tokens.sample(1)[0]
+    if common_prefix_tokens > 0:
+        # Using "." at the end to separate sentences
+        common_prefix_text = (
+            tokenizer.decode(list_of_tokens[: common_prefix_tokens - 2]) + "."
+        )
+        base_offset += common_prefix_tokens
+
+    for conv_id in range(args.num_conversations):
+        # Generate a single conversation
+        messages: MessagesList = []
+
+        nturns = turn_count[conv_id]
+
+        # User prompt token count per turn (with lower limit)
+        input_token_count: np.ndarray = args.input_num_tokens.sample(nturns)
+        input_token_count = np.maximum(input_token_count, base_prompt_token_count)
+
+        # Assistant answer token count per turn (with lower limit)
+        output_token_count: np.ndarray = args.output_num_tokens.sample(nturns)
+        output_token_count = np.maximum(output_token_count, 1)
+
+        user_turn = True
+        for turn_id in range(nturns):
+            if user_turn:
+                role = "user"
+                num_tokens = input_token_count[turn_id]
+
+                # Generate the user prompt,
+                # use a unique prefix (the conv_id) for each conversation
+                # (to avoid shared prefix between conversations)
+                content = f"{conv_id} is a nice number... "
+
+                if len(common_prefix_text) > 0 and turn_id == 0:
+                    content = common_prefix_text + content
+
+                # Update the number of tokens left for the content
+                num_tokens -= len(tokenizer.encode(content, add_special_tokens=False))
+
+                if turn_id == 0:
+                    prefix_num_tokens = conv_prefix_tokens[conv_id]
+                    if prefix_num_tokens > 0:
+                        # Add prefix text (context) to the first turn
+                        start_offset = base_offset
+                        end_offset = start_offset + prefix_num_tokens
+                        assert len(list_of_tokens) > end_offset, (
+                            "Not enough input text to generate "
+                            f"{prefix_num_tokens} tokens for the "
+                            f"prefix text ({start_offset=}, {end_offset=})"
+                        )
+
+                        content += f"{conv_id}, " + tokenizer.decode(
+                            list_of_tokens[start_offset:end_offset]
+                        )
+                        base_offset += prefix_num_tokens
+
+                # Add the actual user prompt/question after the prefix text
+                content += base_prompt_text
+                num_tokens -= base_prompt_token_count
+
+                if num_tokens > 0:
+                    # Add text from the input file (to reach the desired token count)
+                    start_offset = base_offset + turn_id * input_token_count.max()
+                    end_offset = start_offset + num_tokens
+                    assert len(list_of_tokens) > end_offset, (
+                        f"Not enough input text to generate {num_tokens} tokens "
+                        f"for the prompt ({start_offset=}, {end_offset=})"
+                    )
+
+                    # Convert tokens back to text
+                    content += tokenizer.decode(list_of_tokens[start_offset:end_offset])
+            else:
+                role = "assistant"
+                # This content will not be used as input to the LLM server
+                # (actual answers will be used instead).
+                # Content is only required to determine the min_tokens/max_tokens
+                # (inputs to the LLM server).
+                num_tokens = output_token_count[turn_id]
+                assert len(list_of_tokens) > num_tokens, (
+                    f"Not enough input text to generate {num_tokens} "
+                    "tokens for assistant content"
+                )
+                content = tokenizer.decode(list_of_tokens[:num_tokens])
+
+            # Append the user/assistant message to the list of messages
+            messages.append({"role": role, "content": content})
+            user_turn = not user_turn
+
+        # Add the new conversation
+        conversations[f"CONV_ID_{conv_id}"] = messages
+
+        # Increase base offset for the next conversation
+        base_offset += nturns
+
+    if args.print_stats:
+        print_conv_stats(conversations, tokenizer)
+
+    return conversations
+
+
+def conversations_list_to_dict(input_list: ShareGptConversations) -> ConversationsMap:
+    conversations: ConversationsMap = {}
+
+    for item in input_list:
+        conv_id: str = item["id"]
+        assert isinstance(conv_id, str)
+
+        assert conv_id not in conversations, (
+            f"Conversation ID {conv_id} found more than once in the input"
+        )
+
+        messages: MessagesList = item["messages"]
+        assert isinstance(messages, list), (
+            f"Conversation messages should be a list (ID: {conv_id})"
+        )
+        assert len(messages) > 0, f"Conversation with no messages (ID: {conv_id})"
+
+        conversations[conv_id] = messages
+
+    logger.info(f"Using {len(conversations)} unique conversations (IDs)")
+    assert len(conversations) == len(input_list)
+
+    # Print statistics about the selected conversations
+    stats: list[dict[str, Any]] = []
+    for conv_data in conversations.values():
+        stats.append({"num_turns": len(conv_data)})
+
+    print(TEXT_SEPARATOR)
+    print(f"{Color.YELLOW}Conversations statistics:{Color.RESET}")
+    print(TEXT_SEPARATOR)
+    percentiles = [0.25, 0.5, 0.75, 0.9, 0.99, 0.999, 0.9999]
+    conv_stats = pd.DataFrame(stats).describe(percentiles=percentiles)
+    print(conv_stats.transpose())
+    print(TEXT_SEPARATOR)
+
+    return conversations
+
+
+def conversations_dict_to_list(input_dict: ConversationsMap) -> ShareGptConversations:
+    output: ShareGptConversations = []
+    for conv_id, conv_data in input_dict.items():
+        new_item = {"id": conv_id, "messages": conv_data}
+        output.append(new_item)
+
+    return output
--- a/benchmarks/multi_turn/bench_utils.py
+++ b/benchmarks/multi_turn/bench_utils.py
@ -0,0 +1,28 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+import logging
+from enum import Enum
+
+
+class Color(Enum):
+    RED = "\033[91m"
+    GREEN = "\033[92m"
+    BLUE = "\033[94m"
+    PURPLE = "\033[95m"
+    CYAN = "\033[96m"
+    YELLOW = "\033[93m"
+    RESET = "\033[0m"
+
+    def __str__(self):
+        return self.value
+
+
+TEXT_SEPARATOR = "-" * 100
+
+# Configure the logger
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s [%(levelname)s] - %(message)s",
+    datefmt="%d-%m-%Y %H:%M:%S",
+)
+logger = logging.getLogger(__name__)
--- a/benchmarks/multi_turn/benchmark_serving_multi_turn.py
+++ b/benchmarks/multi_turn/benchmark_serving_multi_turn.py
--- a/benchmarks/multi_turn/convert_sharegpt_to_openai.py
+++ b/benchmarks/multi_turn/convert_sharegpt_to_openai.py
@ -0,0 +1,354 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+"""
+Download dataset from:
+https://huggingface.co/datasets/philschmid/sharegpt-raw/blob/main/sharegpt_20230401_clean_lang_split.json
+
+Convert to OpenAI API:
+export INPUT_FILE=sharegpt_20230401_clean_lang_split.json
+python convert_sharegpt_to_openai.py $INPUT_FILE sharegpt_conv_128.json --max-items=128
+"""
+
+import argparse
+import json
+import random
+from statistics import mean
+from typing import Any, Optional
+
+import pandas as pd  # type: ignore
+import tqdm  # type: ignore
+from transformers import AutoTokenizer  # type: ignore
+
+
+def has_non_english_chars(text: str) -> bool:
+    return not text.isascii()
+
+
+def content_is_valid(
+    content: str, min_content_len: Optional[int], max_content_len: Optional[int]
+) -> bool:
+    if min_content_len and len(content) < min_content_len:
+        return False
+
+    if max_content_len and len(content) > max_content_len:
+        return False
+
+    return has_non_english_chars(content)
+
+
+def print_stats(
+    conversations: "list[dict[Any, Any]]", tokenizer: Optional[AutoTokenizer] = None
+) -> None:
+    # Collect statistics
+    stats = []
+
+    print("\nCollecting statistics...")
+    for item in tqdm.tqdm(conversations):
+        # item has "id" and "messages"
+        messages = item["messages"]
+
+        user_turns = 0
+        assistant_turns = 0
+        user_words = 0
+        assistant_words = 0
+        conv_chars = 0
+
+        user_tokens: list[int] = []
+        assistant_tokens: list[int] = []
+
+        for m in messages:
+            content = m["content"]
+            conv_chars += len(content)
+            content_num_words = content.count(" ") + 1
+
+            num_tokens = 0
+            if tokenizer:
+                num_tokens = len(tokenizer(m["content"]).input_ids)
+
+            if m["role"] == "user":
+                user_turns += 1
+                user_words += content_num_words
+                if tokenizer:
+                    user_tokens.append(num_tokens)
+
+            elif m["role"] == "assistant":
+                assistant_turns += 1
+                assistant_words += content_num_words
+                if tokenizer:
+                    assistant_tokens.append(num_tokens)
+
+        # assert user_turns == assistant_turns, \
+        # f"Invalid conversation ID {item['id']}"
+
+        conv_words = user_words + assistant_words
+        item_stats = {
+            "user_turns": user_turns,
+            "assistant_turns": assistant_turns,
+            "user_words": user_words,
+            "assistant_words": assistant_words,
+            "conv_turns": len(messages),
+            "conv_words": conv_words,
+            "conv_characters": conv_chars,
+        }
+
+        if len(user_tokens) > 0:
+            item_stats["user_tokens"] = int(mean(user_tokens))
+
+        if len(assistant_tokens) > 0:
+            item_stats["assistant_tokens"] = int(mean(assistant_tokens))
+
+        stats.append(item_stats)
+
+    print("\nStatistics:")
+    percentiles = [0.25, 0.5, 0.75, 0.9, 0.99, 0.999, 0.9999]
+    df = pd.DataFrame(stats)
+    print(df.describe(percentiles=percentiles).transpose())
+
+
+def convert_sharegpt_to_openai(
+    seed: int,
+    input_file: str,
+    output_file: str,
+    max_items: Optional[int],
+    min_content_len: Optional[int] = None,
+    max_content_len: Optional[int] = None,
+    min_turns: Optional[int] = None,
+    max_turns: Optional[int] = None,
+    model: Optional[str] = None,
+) -> None:
+    if min_turns and max_turns:
+        assert min_turns <= max_turns
+
+    if min_content_len and max_content_len:
+        # Verify that min is not larger than max if both were given
+        assert min_content_len <= max_content_len
+
+    print(
+        f"Input parameters:\n{seed=}, {max_items=}, {min_content_len=},"
+        f" {max_content_len=}, {min_turns=}, {max_turns=}\n"
+    )
+
+    random.seed(seed)
+
+    tokenizer = None
+    if model is not None:
+        print(f"Loading tokenizer from: {model}")
+        tokenizer = AutoTokenizer.from_pretrained(model)
+
+    # Read the ShareGPT JSON file
+    print(f"Reading file: {input_file}")
+    with open(input_file, encoding="utf-8") as f:
+        # Should be a list of dicts
+        # Each dict should have "id" (string) and "conversations" (list of dicts)
+        sharegpt_data = json.load(f)
+
+    assert isinstance(sharegpt_data, list), "Input file should contain a list of dicts"
+
+    print(f"Total items in input file: {len(sharegpt_data):,}")
+
+    print(f"Shuffling dataset with seed {seed}")
+    random.shuffle(sharegpt_data)
+
+    # Map conversation ID to the all the messages
+    conversation_parts: dict[str, list[Any]] = {}
+
+    for item in tqdm.tqdm(sharegpt_data):
+        assert "id" in item, "Missing key 'id'"
+        assert "conversations" in item, "Missing key 'conversations'"
+
+        # Conversation ID (e.g: "hiWPlMD") and part/session (0, 1, 2, etc.)
+        conv_id, _ = item["id"].split("_")
+        new_turns = item["conversations"]
+
+        if conv_id not in conversation_parts:
+            # Start new conversation
+            conversation_parts[conv_id] = []
+        elif len(conversation_parts[conv_id]) > 0 and len(new_turns) > 0:
+            prev_turns = conversation_parts[conv_id][-1]
+            if prev_turns[-1]["from"] == new_turns[0]["from"]:
+                new_turns = new_turns[1:]
+
+        if len(new_turns) > 0:
+            # We assume that parts are in order in the ShareGPT dataset
+            conversation_parts[conv_id].append(new_turns)
+
+    dataset: list[dict[str, Any]] = []
+    for conv_id, conv_parts in conversation_parts.items():
+        new_item = {"id": conv_id}
+
+        conversations: list[dict[str, str]] = []
+
+        # Merge all parts
+        for conv_part in conv_parts:
+            conversations.extend(conv_part)
+
+        if len(conversations) > 0:
+            new_item["conversations"] = conversations
+            dataset.append(new_item)
+
+    print(f"Total unique conversations (IDs) in input file: {len(dataset):,}")
+
+    # Final output data
+    final_openai_dataset: list[dict] = []
+
+    # Filter conversations from the ShareGPT dataset and convert to OpenAI format
+    for item in tqdm.tqdm(dataset):
+        messages: list[dict] = []
+
+        assert "id" in item, "Missing key 'id'"
+        assert "conversations" in item, "Missing key 'conversations'"
+
+        conv_id = item["id"]
+        conversations = item["conversations"]
+
+        if min_turns is not None and len(conversations) < min_turns:
+            # Skip short conversations
+            continue
+
+        # Convert each message in the conversation, up to max_turns if specified
+        for i, turn in enumerate(conversations):
+            assert "from" in turn and "value" in turn, (
+                f"Invalid conversation ID {conv_id} - missing 'from' or 'value'"
+            )
+
+            role = None
+            turn_from = turn["from"]
+
+            if turn_from in {"human", "user"}:
+                role = "user"
+            elif turn_from in {"gpt", "bing", "chatgpt", "bard"}:
+                role = "assistant"
+            elif turn_from == "system":
+                role = "system"
+
+            assert role is not None, (
+                f"Invalid conversation ID {conv_id} - 'from'='{turn_from}' is invalid"
+            )
+
+            if i == 0 and role != "user":
+                # If the first message is from assistant (gpt), skip it.
+                # this happens when the conversation is a follow-up
+                # to a previous conversation (from the same user).
+                continue
+
+            if max_turns is not None and i >= max_turns:
+                break
+
+            # Convert message to OpenAI format (with "role" and "content")
+            content = turn["value"]
+            messages.append({"role": role, "content": content})
+
+        # Add the converted conversation to the OpenAI format
+        if len(messages) > 0:
+            valid_messages = True
+
+            # First turn should always be from the user
+            user_turn = True
+
+            for m in messages:
+                # Make sure that turns alternate between user and assistant
+                if (user_turn and m["role"] != "user") or (
+                    not user_turn and m["role"] != "assistant"
+                ):
+                    valid_messages = False
+                    break
+
+                user_turn = not user_turn
+
+                content = m["content"]
+                valid_messages = content_is_valid(
+                    content, min_content_len, max_content_len
+                )
+                if not valid_messages:
+                    break
+
+            if valid_messages is True:
+                final_openai_dataset.append({"id": conv_id, "messages": messages})
+
+    assert len(final_openai_dataset) > 0, "Final number of conversations is zero"
+
+    print_stats(final_openai_dataset)
+
+    print_stats_again = False
+    if max_items is not None and len(final_openai_dataset) > max_items:
+        print(f"\n\nSampling {max_items} items from the dataset...")
+        print_stats_again = True
+        final_openai_dataset = random.sample(final_openai_dataset, max_items)
+
+    if print_stats_again:
+        # Print stats after the dataset changed
+        print_stats(final_openai_dataset, tokenizer)
+
+    # Write the converted data to a new JSON file
+    final_size = len(final_openai_dataset)
+    print(f"\nTotal conversations converted (after filtering): {final_size:,}")
+    print(f"\nWriting file: {output_file}")
+    with open(output_file, "w", encoding="utf-8") as f:
+        json.dump(final_openai_dataset, f, ensure_ascii=False, indent=2)
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(
+        description="Convert ShareGPT dataset to OpenAI API format"
+    )
+    parser.add_argument("input_file", help="Path to the input ShareGPT JSON file")
+    parser.add_argument(
+        "output_file", help="Path to the output OpenAI format JSON file"
+    )
+    parser.add_argument(
+        "--seed", type=int, default=0, help="Seed for random number generators"
+    )
+    parser.add_argument(
+        "--max-items",
+        type=int,
+        default=None,
+        help="Maximum number of items in the output file",
+    )
+    parser.add_argument(
+        "--min-turns",
+        type=int,
+        default=None,
+        help="Minimum number of turns per conversation",
+    )
+    parser.add_argument(
+        "--max-turns",
+        type=int,
+        default=None,
+        help="Maximum number of turns per conversation",
+    )
+    parser.add_argument(
+        "--min-content-len",
+        type=int,
+        default=None,
+        help="Min number of characters in the messages' content",
+    )
+    parser.add_argument(
+        "--max-content-len",
+        type=int,
+        default=None,
+        help="Max number of characters in the messages' content",
+    )
+    parser.add_argument(
+        "--model",
+        type=str,
+        default=None,
+        help="LLM model, only the tokenizer will be used",
+    )
+
+    args = parser.parse_args()
+
+    convert_sharegpt_to_openai(
+        args.seed,
+        args.input_file,
+        args.output_file,
+        args.max_items,
+        args.min_content_len,
+        args.max_content_len,
+        args.min_turns,
+        args.max_turns,
+        args.model,
+    )
+
+
+if __name__ == "__main__":
+    main()
--- a/benchmarks/multi_turn/generate_multi_turn.json
+++ b/benchmarks/multi_turn/generate_multi_turn.json
@ -0,0 +1,35 @@
+{
+    "filetype": "generate_conversations",
+    "num_conversations": 24,
+    "text_files": ["pg1184.txt"],
+    "print_stats": false,
+    "prompt_input": {
+        "num_turns": {
+            "distribution": "uniform",
+            "min": 12,
+            "max": 18
+        },
+        "common_prefix_num_tokens": {
+            "distribution": "constant",
+            "value": 500
+        },
+        "prefix_num_tokens": {
+            "distribution": "lognormal",
+            "mean": 6,
+            "sigma": 4,
+            "max": 1500
+        },
+        "num_tokens": {
+            "distribution": "uniform",
+            "min": 120,
+            "max": 160
+        }
+    },
+    "prompt_output": {
+        "num_tokens": {
+            "distribution": "uniform",
+            "min": 80,
+            "max": 120
+        }
+    }
+}
--- a/benchmarks/multi_turn/requirements.txt
+++ b/benchmarks/multi_turn/requirements.txt
@ -0,0 +1,5 @@
+numpy>=1.24
+pandas>=2.0.0
+aiohttp>=3.10
+transformers>=4.46
+xlsxwriter>=3.2.1
--- a/cmake/cpu_extension.cmake
+++ b/cmake/cpu_extension.cmake
@ -58,6 +58,22 @@ function (find_isa CPUINFO TARGET OUT)
    endif()
 endfunction()

+
+function(check_sysctl TARGET OUT)
+    execute_process(COMMAND sysctl -n "${TARGET}"
+                    RESULT_VARIABLE SYSCTL_RET
+                    OUTPUT_VARIABLE SYSCTL_INFO
+                    ERROR_QUIET
+                    OUTPUT_STRIP_TRAILING_WHITESPACE)
+    if(SYSCTL_RET EQUAL 0 AND
+      (SYSCTL_INFO STREQUAL "1" OR SYSCTL_INFO GREATER 0))
+        set(${OUT} ON PARENT_SCOPE)
+    else()
+        set(${OUT} OFF PARENT_SCOPE)
+    endif()
+endfunction()
+
+
 function (is_avx512_disabled OUT)
    set(DISABLE_AVX512 $ENV{VLLM_CPU_DISABLE_AVX512})
    if(DISABLE_AVX512 AND DISABLE_AVX512 STREQUAL "true")
@ -70,7 +86,10 @@ endfunction()
 is_avx512_disabled(AVX512_DISABLED)

 if (MACOSX_FOUND AND CMAKE_SYSTEM_PROCESSOR STREQUAL "arm64")
-    set(APPLE_SILICON_FOUND TRUE)
+    message(STATUS "Apple Silicon Detected")
+    set(ENABLE_NUMA OFF)
+    check_sysctl(hw.optional.neon ASIMD_FOUND)
+    check_sysctl(hw.optional.arm.FEAT_BF16 ARM_BF16_FOUND)
 else()
    find_isa(${CPUINFO} "avx2" AVX2_FOUND)
    find_isa(${CPUINFO} "avx512f" AVX512_FOUND)
@ -82,7 +101,6 @@ else()
    find_isa(${CPUINFO} "S390" S390_FOUND)
 endif()

-
 if (AVX512_FOUND AND NOT AVX512_DISABLED)
    list(APPEND CXX_COMPILE_FLAGS
        "-mavx512f"
@ -149,9 +167,6 @@ elseif (ASIMD_FOUND)
        set(MARCH_FLAGS "-march=armv8.2-a+dotprod+fp16")  
    endif()
    list(APPEND CXX_COMPILE_FLAGS ${MARCH_FLAGS})     
-elseif(APPLE_SILICON_FOUND)
-    message(STATUS "Apple Silicon Detected")
-    set(ENABLE_NUMA OFF)
 elseif (S390_FOUND)
    message(STATUS "S390 detected")
    # Check for S390 VXE support
@ -167,17 +182,17 @@ endif()
 #
 # Build oneDNN for W8A8 GEMM kernels (only for x86-AVX512 /ARM platforms)
 # Flag to enable ACL kernels for AARCH64 platforms
-if ( VLLM_BUILD_ACL STREQUAL "ON")
+if (VLLM_BUILD_ACL STREQUAL "ON")
    set(USE_ACL ON)
 else()
    set(USE_ACL OFF)
 endif()

-if ((AVX512_FOUND AND NOT AVX512_DISABLED) OR ASIMD_FOUND)
+if ((AVX512_FOUND AND NOT AVX512_DISABLED) OR ASIMD_FOUND OR POWER9_FOUND OR POWER10_FOUND OR POWER11_FOUND)
    FetchContent_Declare(
        oneDNN
        GIT_REPOSITORY https://github.com/oneapi-src/oneDNN.git
-        GIT_TAG  v3.8.1
+        GIT_TAG v3.9
        GIT_PROGRESS TRUE
        GIT_SHALLOW TRUE
    )
@ -189,7 +204,7 @@ if ((AVX512_FOUND AND NOT AVX512_DISABLED) OR ASIMD_FOUND)
        endif()
        set(ONEDNN_AARCH64_USE_ACL "ON")
        set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wl,-rpath,$ENV{ACL_ROOT_DIR}/build/")
-        endif()
+    endif()

    set(ONEDNN_LIBRARY_TYPE "STATIC")
    set(ONEDNN_BUILD_DOC "OFF")
@ -202,38 +217,23 @@ if ((AVX512_FOUND AND NOT AVX512_DISABLED) OR ASIMD_FOUND)
    set(ONEDNN_ENABLE_ITT_TASKS "OFF")
    set(ONEDNN_ENABLE_MAX_CPU_ISA "OFF")
    set(ONEDNN_ENABLE_CPU_ISA_HINTS "OFF")
+    set(ONEDNN_VERBOSE "OFF")
    set(CMAKE_POLICY_DEFAULT_CMP0077 NEW)

    FetchContent_MakeAvailable(oneDNN)
-    
-    list(APPEND LIBS dnnl)
-elseif(POWER10_FOUND)
-    FetchContent_Declare(
-        oneDNN
-        GIT_REPOSITORY https://github.com/oneapi-src/oneDNN.git
-        GIT_TAG v3.7.2
-        GIT_PROGRESS TRUE
-        GIT_SHALLOW TRUE
+    add_library(dnnl_ext OBJECT "csrc/cpu/dnnl_helper.cpp")
+    target_include_directories(
+        dnnl_ext
+        PUBLIC ${oneDNN_SOURCE_DIR}/include
+        PUBLIC ${oneDNN_BINARY_DIR}/include
+        PRIVATE ${oneDNN_SOURCE_DIR}/src
    )
-
-    set(ONEDNN_LIBRARY_TYPE "STATIC")
-    set(ONEDNN_BUILD_DOC "OFF")
-    set(ONEDNN_BUILD_EXAMPLES "OFF")
-    set(ONEDNN_BUILD_TESTS "OFF")
-    set(ONEDNN_ENABLE_WORKLOAD "INFERENCE")
-    set(ONEDNN_ENABLE_PRIMITIVE "MATMUL;REORDER")
-    set(ONEDNN_BUILD_GRAPH "OFF")
-    set(ONEDNN_ENABLE_JIT_PROFILING "OFF")
-    set(ONEDNN_ENABLE_ITT_TASKS "OFF")
-    set(ONEDNN_ENABLE_MAX_CPU_ISA "OFF")
-    set(ONEDNN_ENABLE_CPU_ISA_HINTS "OFF")
-    set(CMAKE_POLICY_DEFAULT_CMP0077 NEW)
-
-    set(DNNL_CPU_RUNTIME "OMP")
-
-    FetchContent_MakeAvailable(oneDNN)
-
-    list(APPEND LIBS dnnl)
+    target_link_libraries(dnnl_ext dnnl)
+    target_compile_options(dnnl_ext PRIVATE ${CXX_COMPILE_FLAGS} -fPIC)
+    list(APPEND LIBS dnnl_ext)
+    set(USE_ONEDNN ON)
+else()
+    set(USE_ONEDNN OFF)
 endif()

 message(STATUS "CPU extension compile flags: ${CXX_COMPILE_FLAGS}")
@ -260,7 +260,6 @@ set(VLLM_EXT_SRC

 if (AVX512_FOUND AND NOT AVX512_DISABLED)
    set(VLLM_EXT_SRC
-        "csrc/cpu/quant.cpp"
        "csrc/cpu/shm.cpp"
        ${VLLM_EXT_SRC})
    if (ENABLE_AVX512BF16 AND ENABLE_AVX512VNNI)
@ -274,14 +273,11 @@ if (AVX512_FOUND AND NOT AVX512_DISABLED)
            ${VLLM_EXT_SRC})
        add_compile_definitions(-DCPU_CAPABILITY_AVX512)
    endif()
-elseif(POWER10_FOUND)
-    set(VLLM_EXT_SRC
-        "csrc/cpu/quant.cpp"
-        ${VLLM_EXT_SRC})
 endif()
-if (ASIMD_FOUND)
+
+if(USE_ONEDNN)
    set(VLLM_EXT_SRC
-        "csrc/cpu/quant.cpp"
+        "csrc/cpu/dnnl_kernels.cpp"
        ${VLLM_EXT_SRC})
 endif()

--- a/cmake/external_projects/flashmla.cmake
+++ b/cmake/external_projects/flashmla.cmake
@ -19,7 +19,7 @@ else()
  FetchContent_Declare(
        flashmla
        GIT_REPOSITORY https://github.com/vllm-project/FlashMLA.git
-        GIT_TAG 575f7724b9762f265bbee5889df9c7d630801845
+        GIT_TAG 0e43e774597682284358ff2c54530757b654b8d1
        GIT_PROGRESS TRUE
        CONFIGURE_COMMAND ""
        BUILD_COMMAND ""
@ -37,9 +37,9 @@ cuda_archs_loose_intersection(FLASH_MLA_ARCHS "9.0a" "${CUDA_ARCHS}")
 if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER 12.3 AND FLASH_MLA_ARCHS)
    set(FlashMLA_SOURCES
        ${flashmla_SOURCE_DIR}/csrc/flash_api.cpp
-        ${flashmla_SOURCE_DIR}/csrc/flash_fwd_mla_bf16_sm90.cu
-        ${flashmla_SOURCE_DIR}/csrc/flash_fwd_mla_fp16_sm90.cu
-        ${flashmla_SOURCE_DIR}/csrc/flash_fwd_mla_metadata.cu)
+        ${flashmla_SOURCE_DIR}/csrc/kernels/splitkv_mla.cu
+        ${flashmla_SOURCE_DIR}/csrc/kernels/mla_combine.cu
+        ${flashmla_SOURCE_DIR}/csrc/kernels/get_mla_metadata.cu)

    set(FlashMLA_INCLUDES
        ${flashmla_SOURCE_DIR}/csrc/cutlass/include
--- a/cmake/external_projects/vllm_flash_attn.cmake
+++ b/cmake/external_projects/vllm_flash_attn.cmake
@ -38,7 +38,7 @@ else()
  FetchContent_Declare(
          vllm-flash-attn
          GIT_REPOSITORY https://github.com/vllm-project/flash-attention.git
-          GIT_TAG 1c2624e53c078854e0637ee566c72fe2107e75f4
+          GIT_TAG 57b4e68b9f9d94750b46de8f8dbd2bfcc86edd4f
          GIT_PROGRESS TRUE
          # Don't share the vllm-flash-attn build between build types
          BINARY_DIR ${CMAKE_BINARY_DIR}/vllm-flash-attn
--- a/cmake/utils.cmake
+++ b/cmake/utils.cmake
@ -467,6 +467,12 @@ function (define_gpu_extension_target GPU_MOD_NAME)
  if (GPU_LANGUAGE STREQUAL "HIP")
    # Make this target dependent on the hipify preprocessor step.
    add_dependencies(${GPU_MOD_NAME} hipify${GPU_MOD_NAME})
+    # Make sure we include the hipified versions of the headers, and avoid conflicts with the ones in the original source folder
+    target_include_directories(${GPU_MOD_NAME} PRIVATE ${CMAKE_CURRENT_BINARY_DIR}/csrc
+      ${GPU_INCLUDE_DIRECTORIES})
+  else()
+    target_include_directories(${GPU_MOD_NAME} PRIVATE csrc
+      ${GPU_INCLUDE_DIRECTORIES})
  endif()

  if (GPU_ARCHITECTURES)
@ -482,8 +488,6 @@ function (define_gpu_extension_target GPU_MOD_NAME)
  target_compile_definitions(${GPU_MOD_NAME} PRIVATE
    "-DTORCH_EXTENSION_NAME=${GPU_MOD_NAME}")

-  target_include_directories(${GPU_MOD_NAME} PRIVATE csrc
-    ${GPU_INCLUDE_DIRECTORIES})

  target_link_libraries(${GPU_MOD_NAME} PRIVATE torch ${GPU_LIBRARIES})

--- a/csrc/activation_kernels.cu
+++ b/csrc/activation_kernels.cu
@ -128,6 +128,45 @@ __global__ void act_and_mul_kernel_with_param(
  }
 }

+template <typename T>
+__device__ __forceinline__ T swigluoai_and_mul(const T& gate, const T& up,
+                                               float alpha, float limit) {
+  // clamp gate: min=None, max=limit
+  const float gate_f = (float)gate;
+  const float clamped_gate = gate_f > limit ? limit : gate_f;
+
+  // clamp up: min=-limit, max=limit
+  const float up_f = (float)up;
+  const float clamped_up =
+      up_f > limit ? limit : (up_f < -limit ? -limit : up_f);
+
+  // glu = gate * sigmoid(gate * alpha)
+  const float sigmoid_val = 1.0f / (1.0f + expf(-clamped_gate * alpha));
+  const float glu = clamped_gate * sigmoid_val;
+
+  // (up + 1) * glu
+  return (T)((clamped_up + 1.0f) * glu);
+}
+
+template <typename scalar_t,
+          scalar_t (*ACT_FN)(const scalar_t&, const scalar_t&, const float,
+                             const float)>
+__global__ void swigluoai_and_mul_kernel(
+    scalar_t* __restrict__ out,          // [..., d]
+    const scalar_t* __restrict__ input,  // [..., 2, d]
+    const int d, const float alpha, const float limit) {
+  const int64_t token_idx = blockIdx.x;
+  // TODO: Vectorize loads and stores.
+  for (int64_t idx = threadIdx.x; idx < d; idx += blockDim.x) {
+    // gate = x[..., ::2]  (even indices)
+    const scalar_t gate = VLLM_LDG(&input[token_idx * 2 * d + 2 * idx]);
+    // up = x[..., 1::2]   (odd indices)
+    const scalar_t up = VLLM_LDG(&input[token_idx * 2 * d + 2 * idx + 1]);
+
+    out[token_idx * d + idx] = ACT_FN(gate, up, alpha, limit);
+  }
+}
+
 }  // namespace vllm

 #define LAUNCH_ACTIVATION_GATE_KERNEL_WITH_PARAM(KERNEL, PARAM)         \
@ -145,11 +184,31 @@ __global__ void act_and_mul_kernel_with_param(
                                         PARAM);                        \
      });

+#define LAUNCH_SIGLUOAI_AND_MUL(KERNEL, ALPHA, LIMIT)                          \
+  int d = input.size(-1) / 2;                                                  \
+  int64_t num_tokens = input.numel() / input.size(-1);                         \
+  dim3 grid(num_tokens);                                                       \
+  dim3 block(std::min(d, 1024));                                               \
+  const at::cuda::OptionalCUDAGuard device_guard(device_of(input));            \
+  const cudaStream_t stream = at::cuda::getCurrentCUDAStream();                \
+  VLLM_DISPATCH_FLOATING_TYPES(                                                \
+      input.scalar_type(), "clamp_swiglu_kernel_with_params", [&] {            \
+        vllm::swigluoai_and_mul_kernel<scalar_t, KERNEL<scalar_t>>             \
+            <<<grid, block, 0, stream>>>(out.data_ptr<scalar_t>(),             \
+                                         input.data_ptr<scalar_t>(), d, ALPHA, \
+                                         LIMIT);                               \
+      });
+
 void fatrelu_and_mul(torch::Tensor& out,    // [..., d],
                     torch::Tensor& input,  // [..., 2 * d]
                     double threshold) {
  LAUNCH_ACTIVATION_GATE_KERNEL_WITH_PARAM(vllm::fatrelu_kernel, threshold);
 }
+void swigluoai_and_mul(torch::Tensor& out,    // [..., d]
+                       torch::Tensor& input,  // [..., 2 * d]
+                       double alpha, double limit) {
+  LAUNCH_SIGLUOAI_AND_MUL(vllm::swigluoai_and_mul, alpha, limit);
+}
 namespace vllm {

 // Element-wise activation kernel template.
--- a/csrc/attention/attention_kernels.cuh
+++ b/csrc/attention/attention_kernels.cuh
@ -24,7 +24,7 @@

 #include "attention_dtypes.h"
 #include "attention_utils.cuh"
-#include "cuda_compat.h"
+#include "../cuda_compat.h"

 #ifdef USE_ROCM
  #include <hip/hip_bf16.h>
--- a/csrc/attention/mla/sm100_cutlass_mla_kernel.cu
+++ b/csrc/attention/mla/sm100_cutlass_mla_kernel.cu
@ -167,7 +167,7 @@ typename T::Fmha::Arguments args_from_options(
      // TODO(trevor-m): Change split_kv back to -1 when
      // https://github.com/NVIDIA/cutlass/issues/2274 is fixed. Split_kv=1 will
      // perform worse with larger context length and smaller batch sizes.
-      num_kv_splits, // split_kv
+      static_cast<int>(num_kv_splits), // split_kv
      nullptr,       // is_var_split_kv
  };
  // TODO(kaixih@nvidia): When split_kv=-1 and is_var_split_kv=false, we compute
@ -264,7 +264,7 @@ int64_t sm100_cutlass_mla_get_workspace_size(int64_t max_seq_len, int64_t num_ba
  // Assumes device 0 when getting sm_count.
  arguments.hw_info.sm_count =
      sm_count <= 0 ? cutlass::KernelHardwareInfo::query_device_multiprocessor_count(/*device_id=*/0) : sm_count;
-  arguments.split_kv = num_kv_splits;
+  arguments.split_kv = static_cast<int>(num_kv_splits);
  MlaSm100Type::Fmha::set_split_kv(arguments);

  return MlaSm100Type::Fmha::get_workspace_size(arguments);
--- a/csrc/attention/paged_attention_v1.cu
+++ b/csrc/attention/paged_attention_v1.cu
@ -16,9 +16,8 @@
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
-
 #include "attention_kernels.cuh"
-#include "cuda_compat.h"
+#include "../cuda_compat.h"

 #define MAX(a, b) ((a) > (b) ? (a) : (b))
 #define MIN(a, b) ((a) < (b) ? (a) : (b))
@ -75,7 +74,7 @@ void paged_attention_v1_launcher(
  const float* k_scale_ptr = reinterpret_cast<const float*>(k_scale.data_ptr());
  const float* v_scale_ptr = reinterpret_cast<const float*>(v_scale.data_ptr());

-  constexpr int NUM_WARPS = NUM_THREADS / WARP_SIZE;
+  const int NUM_WARPS = NUM_THREADS / WARP_SIZE;
  int padded_max_seq_len =
      DIVIDE_ROUND_UP(max_seq_len, BLOCK_SIZE) * BLOCK_SIZE;
  int logits_size = padded_max_seq_len * sizeof(float);
--- a/csrc/attention/paged_attention_v2.cu
+++ b/csrc/attention/paged_attention_v2.cu
@ -16,9 +16,8 @@
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
-
 #include "attention_kernels.cuh"
-#include "cuda_compat.h"
+#include "../cuda_compat.h"

 #define MAX(a, b) ((a) > (b) ? (a) : (b))
 #define MIN(a, b) ((a) < (b) ? (a) : (b))
@ -79,7 +78,7 @@ void paged_attention_v2_launcher(
  const float* k_scale_ptr = reinterpret_cast<const float*>(k_scale.data_ptr());
  const float* v_scale_ptr = reinterpret_cast<const float*>(v_scale.data_ptr());

-  constexpr int NUM_WARPS = NUM_THREADS / WARP_SIZE;
+  const int NUM_WARPS = NUM_THREADS / WARP_SIZE;
  int max_num_partitions = DIVIDE_ROUND_UP(max_seq_len, PARTITION_SIZE);
  int logits_size = PARTITION_SIZE * sizeof(float);
  int outputs_size = (NUM_WARPS / 2) * head_size * sizeof(float);
--- a/csrc/cache_kernels.cu
+++ b/csrc/cache_kernels.cu
@ -5,6 +5,7 @@
 #include "cuda_utils.h"
 #include "cuda_compat.h"
 #include "dispatch_utils.h"
+#include "quantization/vectorization_utils.cuh"

 #ifdef USE_ROCM
  #include "quantization/fp8/amd/quant_utils.cuh"
@ -261,14 +262,26 @@ __global__ void reshape_and_cache_kernel(
  }
 }

+// Used by vectorization_utils to copy/convert one element
+template <typename OutT, typename InT, Fp8KVCacheDataType kv_dt>
+struct CopyWithScaleOp {
+  float scale;
+
+  __device__ __forceinline__ void operator()(OutT& dst, const InT src) const {
+    if constexpr (kv_dt == Fp8KVCacheDataType::kAuto) {
+      dst = static_cast<OutT>(src);
+    } else {
+      dst = fp8::scaled_convert<OutT, InT, kv_dt>(src, scale);
+    }
+  }
+};
+
 template <typename scalar_t, typename cache_t, Fp8KVCacheDataType kv_dt>
 __global__ void reshape_and_cache_flash_kernel(
    const scalar_t* __restrict__ key,    // [num_tokens, num_heads, head_size]
    const scalar_t* __restrict__ value,  // [num_tokens, num_heads, head_size]
-    cache_t* __restrict__ key_cache,     // [num_blocks, block_size, num_heads,
-                                         // head_size]
-    cache_t* __restrict__ value_cache,   // [num_blocks, block_size, num_heads,
-                                         // head_size]
+    cache_t* __restrict__ key_cache,     // NHD or HND, shape see comments below
+    cache_t* __restrict__ value_cache,   // same above
    const int64_t* __restrict__ slot_mapping,  // [num_tokens]
    const int64_t block_stride, const int64_t page_stride,
    const int64_t head_stride, const int64_t key_stride,
@ -282,25 +295,58 @@ __global__ void reshape_and_cache_flash_kernel(
  }
  const int64_t block_idx = slot_idx / block_size;
  const int64_t block_offset = slot_idx % block_size;
-  const int n = num_heads * head_size;
-  for (int i = threadIdx.x; i < n; i += blockDim.x) {
-    const int64_t src_key_idx = token_idx * key_stride + i;
-    const int64_t src_value_idx = token_idx * value_stride + i;
-    const int head_idx = i / head_size;
-    const int head_offset = i % head_size;
-    const int64_t tgt_key_value_idx = block_idx * block_stride +
-                                      block_offset * page_stride +
-                                      head_idx * head_stride + head_offset;
-    scalar_t tgt_key = key[src_key_idx];
-    scalar_t tgt_value = value[src_value_idx];
-    if constexpr (kv_dt == Fp8KVCacheDataType::kAuto) {
-      key_cache[tgt_key_value_idx] = tgt_key;
-      value_cache[tgt_key_value_idx] = tgt_value;
-    } else {
-      key_cache[tgt_key_value_idx] =
-          fp8::scaled_convert<cache_t, scalar_t, kv_dt>(tgt_key, *k_scale);
-      value_cache[tgt_key_value_idx] =
-          fp8::scaled_convert<cache_t, scalar_t, kv_dt>(tgt_value, *v_scale);
+  const int n_elems = num_heads * head_size;
+
+  // pointers to the beginning of the source row for this token.
+  const scalar_t* __restrict__ key_src = key + token_idx * key_stride;
+  const scalar_t* __restrict__ value_src = value + token_idx * value_stride;
+
+  // find the start position inside the kv-cache for this token.
+  cache_t* __restrict__ key_dst =
+      key_cache + block_idx * block_stride + block_offset * page_stride;
+  cache_t* __restrict__ value_dst =
+      value_cache + block_idx * block_stride + block_offset * page_stride;
+
+  // this is true for the NHD layout where `head_stride == head_size`
+  const bool is_contiguous_heads = (head_stride == head_size);
+
+  float k_scale_val = (kv_dt == Fp8KVCacheDataType::kAuto) ? 0.f : *k_scale;
+  float v_scale_val = (kv_dt == Fp8KVCacheDataType::kAuto) ? 0.f : *v_scale;
+  constexpr int VEC_SIZE = (sizeof(scalar_t) == 2) ? 8 : 4;
+  CopyWithScaleOp<cache_t, scalar_t, kv_dt> k_op{k_scale_val};
+  CopyWithScaleOp<cache_t, scalar_t, kv_dt> v_op{v_scale_val};
+  if (is_contiguous_heads) {
+    // NHD layout
+    // kv cache: [num_blocks, block_size, num_heads, head_size]
+    vectorize_with_alignment<VEC_SIZE>(key_src, key_dst, n_elems, threadIdx.x,
+                                       blockDim.x, k_op);
+
+    vectorize_with_alignment<VEC_SIZE>(value_src, value_dst, n_elems,
+                                       threadIdx.x, blockDim.x, v_op);
+
+  } else {
+    // HND layout: heads are strided, but each head_size segment is contiguous
+    // kv cache: [num_blocks, num_heads, block_size, head_size]
+    const int lane = threadIdx.x & 31;     // 0..31 within warp
+    const int warp_id = threadIdx.x >> 5;  // warp index within block
+    const int warps_per_block = blockDim.x >> 5;
+
+    for (int head = warp_id; head < num_heads; head += warps_per_block) {
+      const scalar_t* __restrict__ k_src_h = key_src + head * head_size;
+      const scalar_t* __restrict__ v_src_h = value_src + head * head_size;
+
+      cache_t* __restrict__ k_dst_h =
+          key_dst + static_cast<int64_t>(head) * head_stride;
+      cache_t* __restrict__ v_dst_h =
+          value_dst + static_cast<int64_t>(head) * head_stride;
+
+      // within each head, let the 32 threads of the warp perform the vector
+      // copy
+      vectorize_with_alignment<VEC_SIZE>(k_src_h, k_dst_h, head_size, lane, 32,
+                                         k_op);
+
+      vectorize_with_alignment<VEC_SIZE>(v_src_h, v_dst_h, head_size, lane, 32,
+                                         v_op);
    }
  }
 }
--- a/Show More
+++ b/Show More