updated

Signed-off-by: Robert Shaw <robshaw@redhat.com>

.buildkite/nightly-benchmarks/README.md

@@ -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.
 
@@ -149,6 +152,7 @@ Here is an example using the script to compare result_a and result_b without det
 
 Here is an example using the script to compare result_a and result_b with detail test name.
 `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 |
@@ -164,9 +168,9 @@ 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 +180,6 @@ 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).

.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`.

.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
 

.buildkite/nightly-benchmarks/performance-benchmarks-descriptions.md

@@ -1,3 +1,4 @@
+# Performance benchmarks descriptions
 
 ## Latency tests
 

.buildkite/nightly-benchmarks/scripts/convert-results-json-to-markdown.py

@@ -44,6 +44,7 @@ serving_column_mapping = {
     "test_name": "Test name",
     "gpu_type": "GPU",
     "completed": "# of req.",
+    "max_concurrency": "# of max concurrency.",
     "request_throughput": "Tput (req/s)",
     "total_token_throughput": "Total Token Tput (tok/s)",
     "output_throughput": "Output Tput (tok/s)",
@@ -100,7 +101,7 @@ if __name__ == "__main__":
             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:
@@ -120,7 +121,7 @@ if __name__ == "__main__":
             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 +149,7 @@ 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:

.buildkite/nightly-benchmarks/scripts/run-nightly-benchmarks.sh

@@ -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 \

.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
@@ -205,7 +206,7 @@ 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 +232,7 @@ 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
@@ -272,7 +273,7 @@ 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 +298,7 @@ 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
@@ -393,7 +394,7 @@ run_serving_tests() {
 
       # pass the tensor parallel size to the client so that it can be displayed
       # on the benchmark dashboard
-      client_command="python3 benchmark_serving.py \
+      client_command="vllm bench serve \
         --save-result \
         --result-dir $RESULTS_FOLDER \
         --result-filename ${new_test_name}.json \
@@ -447,7 +448,7 @@ 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"

.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"
         },

.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"
         },

.buildkite/nightly-benchmarks/tests/serving-tests-cpu-snc2.json

@@ -0,0 +1,203 @@
+[
+    {
+        "test_name": "serving_llama8B_tp1_sharegpt",
+        "qps_list": [1, 4, 16, "inf"],
+        "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",
+            "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/Meta-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"],
+        "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",
+            "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/Meta-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"],
+        "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",
+            "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/Meta-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_tp1_random_128_128",
+        "qps_list": [1, 4, 16, "inf"],
+        "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",
+            "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/Meta-Llama-3.1-8B-Instruct",
+            "backend": "vllm",
+            "dataset_name": "random",
+	    "random-input-len": 128,
+	    "random-output-len": 128,
+	    "ignore-eos": "",
+	    "max_concurrency": 1000,
+            "num_prompts": 1000
+        }
+    },
+    {
+        "test_name": "serving_llama8B_tp2_random_128_128",
+        "qps_list": [1, 4, 16, "inf"],
+        "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",
+            "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/Meta-Llama-3.1-8B-Instruct",
+            "backend": "vllm",
+            "dataset_name": "random",
+	    "random-input-len": 128,
+	    "random-output-len": 128,
+	    "ignore-eos": "",
+	    "max_concurrency": 1000,
+            "num_prompts": 1000
+        }
+    },
+    {
+        "test_name": "serving_llama8B_tp4_random_128_128",
+        "qps_list": [1, 4, 16, "inf"],
+        "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",
+            "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/Meta-Llama-3.1-8B-Instruct",
+            "backend": "vllm",
+            "dataset_name": "random",
+	    "random-input-len": 128,
+	    "random-output-len": 128,
+	    "ignore-eos": "",
+	    "max_concurrency": 1000,
+            "num_prompts": 1000
+        }
+    }
+]

.buildkite/nightly-benchmarks/tests/serving-tests-cpu-snc3.json

@@ -0,0 +1,205 @@
+[
+    {
+        "test_name": "serving_llama8B_pp1_sharegpt",
+        "qps_list": [1, 4, 16, "inf"],
+        "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",
+            "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/Meta-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_pp3_sharegpt",
+        "qps_list": [1, 4, 16, "inf"],
+        "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",
+            "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/Meta-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_tp2pp6_sharegpt",
+        "qps_list": [1, 4, 16, "inf"],
+        "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",
+            "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/Meta-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_pp1_random_128_128",
+        "qps_list": [1, 4, 16, "inf"],
+        "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",
+            "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/Meta-Llama-3.1-8B-Instruct",
+            "backend": "vllm",
+            "dataset_name": "random",
+	    "random-input-len": 128,
+	    "random-output-len": 128,
+	    "ignore-eos": "",
+	    "max_concurrency": 1000,
+            "num_prompts": 1000
+        }
+    },
+    {
+        "test_name": "serving_llama8B_pp3_random_128_128",
+        "qps_list": [1, 4, 16, "inf"],
+        "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",
+            "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/Meta-Llama-3.1-8B-Instruct",
+            "backend": "vllm",
+            "dataset_name": "random",
+	    "random-input-len": 128,
+	    "random-output-len": 128,
+	    "ignore-eos": "",
+	    "max_concurrency": 1000,
+            "num_prompts": 1000
+        }
+    },
+    {
+        "test_name": "serving_llama8B_tp2pp3_random_128_128",
+        "qps_list": [1, 4, 16, "inf"],
+        "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",
+            "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/Meta-Llama-3.1-8B-Instruct",
+            "backend": "vllm",
+            "dataset_name": "random",
+	    "random-input-len": 128,
+	    "random-output-len": 128,
+	    "ignore-eos": "",
+	    "max_concurrency": 1000,
+            "num_prompts": 1000
+        }
+    }
+]

.buildkite/nightly-benchmarks/tests/serving-tests-cpu.json

@@ -6,6 +6,7 @@
             "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": {
@@ -16,8 +17,9 @@
 	    "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": {
@@ -36,6 +38,7 @@
             "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": {
@@ -46,8 +49,9 @@
 	    "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": {
@@ -66,6 +70,7 @@
             "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": {
@@ -76,8 +81,9 @@
 	    "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": {
@@ -96,6 +102,7 @@
             "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": {
@@ -107,8 +114,9 @@
 	    "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": {
@@ -129,6 +137,7 @@
             "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": {
@@ -140,8 +149,9 @@
 	    "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": {

.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": {
@@ -61,7 +58,6 @@
         "qps_list": [2],
         "server_parameters": {
             "model": "meta-llama/Meta-Llama-3.1-70B-Instruct", 
-            "disable_log_requests": "", 
             "tensor_parallel_size": 4,
             "swap_space": 16,
             "speculative_config": {

.buildkite/scripts/hardware_ci/run-cpu-test.sh

@@ -78,23 +78,23 @@ 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.

.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; }

.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 \

.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

.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 \

.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

.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;
 }
 

.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

.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 \

.buildkite/test-pipeline.yaml

@@ -57,20 +57,20 @@ 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 +82,7 @@ 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:
@@ -99,7 +99,7 @@ steps:
   - VLLM_TEST_ENABLE_ARTIFICIAL_PREEMPT=1 pytest -v -s basic_correctness/test_preemption.py
 
 - label: Chunked Prefill Test
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   source_file_dependencies:
   - vllm/
   - tests/basic_correctness/test_chunked_prefill
@@ -108,7 +108,7 @@ steps:
   - 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 +128,10 @@ 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
@@ -210,7 +209,7 @@ 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/
@@ -228,16 +227,6 @@ steps:
 ##### fast check tests  #####
 #####  1 GPU test  #####
 
-- label: Regression Test # 5min
-  mirror_hardwares: [amdexperimental, amdproduction]
-  source_file_dependencies:
-  - vllm/
-  - tests/test_regression
-  commands:
-  - pip install modelscope
-  - pytest -v -s test_regression.py
-  working_dir: "/vllm-workspace/tests" # optional
-
 - label: Engine Test # 10min
   mirror_hardwares: [amdexperimental]
   source_file_dependencies:
@@ -281,7 +270,7 @@ 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
@@ -306,7 +295,7 @@ steps:
     - 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]
+  mirror_hardwares: [amdexperimental]
   source_file_dependencies:
   - vllm/
   - tests/prefix_caching
@@ -315,7 +304,7 @@ steps:
 
 
 - label: Platform Tests (CUDA)
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   source_file_dependencies:
   - vllm/
   - tests/cuda
@@ -354,9 +343,10 @@ 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
 
 - label: PyTorch Fullgraph Smoke Test # 9min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   torch_nightly: true
   source_file_dependencies:
   - vllm/
@@ -369,7 +359,7 @@ steps:
   - pytest -v -s compile/piecewise/test_full_cudagraph.py
 
 - label: PyTorch Fullgraph Test # 18min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   torch_nightly: true
   source_file_dependencies:
   - vllm/
@@ -378,7 +368,7 @@ 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 +393,21 @@ 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/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 +415,7 @@ 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 +427,7 @@ 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 +437,7 @@ 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 +445,7 @@ steps:
   - bash scripts/run-benchmarks.sh
 
 - label: Benchmarks CLI Test # 10min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   source_file_dependencies:
   - vllm/
   - tests/benchmarks/
@@ -494,7 +484,7 @@ 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 +492,7 @@ 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 +524,6 @@ 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 +534,10 @@ 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
@@ -580,7 +570,8 @@ steps:
     - 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 --ignore models/multimodal/generation/test_whisper.py --ignore models/multimodal/test_tensor_schema.py models/multimodal -m core_model
+    - pytest -v -s models/multimodal/test_tensor_schema.py -m core_model  # Needs mp_method="spawn"
     - 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
@@ -623,7 +614,7 @@ 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 +634,40 @@ 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/v1/attention/backends/flashinfer.py
+  - vllm/compilation/fusion.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/moe/test_nvfp4_moe.py
+    # Fusion
+    - pytest -v -s tests/compile/test_fusion_all_reduce.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 +738,6 @@ 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 +762,8 @@ 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 +777,7 @@ 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 +790,7 @@ 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

.github/CODEOWNERS

@@ -9,8 +9,7 @@
 /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/multimodal @DarkLight1337 @ywang96
 /vllm/vllm_flash_attn @LucasWilkinson
 /vllm/lora @jeejeelee
@@ -21,7 +20,7 @@ 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
@@ -35,20 +34,41 @@ CMakeLists.txt @tlrmchlsmth @LucasWilkinson
 /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
 
 # 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

.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)

.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/

.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}"

.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
 

.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
+        }
+      ]
+    }
+  ]
+}

.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:

.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
 

.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/

.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

.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:

.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

CMakeLists.txt

@@ -427,6 +427,7 @@ 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 +530,25 @@ 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(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8 AND FP4_ARCHS)
@@ -541,7 +561,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
       SRCS "${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()
@@ -768,6 +788,14 @@ 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}")
@@ -836,17 +864,6 @@ 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

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

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
 

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.

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>
@@ -81,16 +81,17 @@ 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 +99,7 @@ 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 \
@@ -109,7 +110,7 @@ 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
@@ -133,11 +134,11 @@ 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?"}
@@ -145,12 +146,12 @@ If the dataset you want to benchmark is not supported yet in vLLM, even then you
 
 ```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 \
@@ -166,15 +167,15 @@ 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 \
   --model Qwen/Qwen2-VL-7B-Instruct \
   --endpoint /v1/chat/completions \
@@ -184,7 +185,7 @@ 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 \
@@ -194,23 +195,23 @@ 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 \
   --model Qwen/Qwen2-VL-7B-Instruct \
   --endpoint /v1/chat/completions \
@@ -221,10 +222,10 @@ 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 \
   --model Qwen/Qwen2-VL-7B-Instruct \
   --endpoint /v1/chat/completions \
@@ -234,10 +235,10 @@ 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 +246,23 @@ 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 +274,34 @@ 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 +310,16 @@ 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 +330,18 @@ 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 +354,18 @@ 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 +375,10 @@ 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 +387,10 @@ 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 +399,12 @@ 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 +418,22 @@ 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 +445,7 @@ 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 +457,7 @@ 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 +468,7 @@ 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 +479,7 @@ 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 +492,16 @@ 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 +513,7 @@ 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 +546,16 @@ 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 +566,7 @@ python3 benchmarks/benchmark_prefix_caching.py \
   --input-length-range 128:256
 ```
 
-**ShareGPT Dataset with Prefix Caching**
+### ShareGPT Dataset with Prefix Caching
 
 ```bash
 # download dataset
@@ -572,14 +583,16 @@ python3 benchmarks/benchmark_prefix_caching.py \
 
 </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 +603,7 @@ python3 benchmarks/benchmark_prioritization.py \
   --scheduling-policy priority
 ```
 
-**Multiple Sequences per Prompt**
+### Multiple Sequences per Prompt
 
 ```bash
 python3 benchmarks/benchmark_prioritization.py \

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

benchmarks/auto_tune/auto_tune.sh

@@ -4,13 +4,15 @@
 # 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
@@ -48,19 +58,35 @@ start_server() {
     local vllm_log=$4
     local profile_dir=$5
 
-    pkill -f vllm
+    pkill -if 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 &
+    # 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
@@ -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: $max_num_batched_tokens"
@@ -126,8 +136,9 @@ run_benchmark() {
     # get a basic qps by using request-rate inf
     bm_log="$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"
-

benchmarks/backend_request_func.py

@@ -31,7 +31,7 @@ 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
 
@@ -364,7 +364,15 @@ 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
@@ -491,7 +499,10 @@ 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():

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

benchmarks/benchmark_dataset.py

@@ -52,7 +52,7 @@ 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
 
 

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)
 

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

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,
@@ -395,20 +402,6 @@ async def benchmark(
         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 +419,10 @@ 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 +514,20 @@ 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 +604,10 @@ 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)

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
 
 

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

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)

benchmarks/disagg_benchmarks/disagg_overhead_benchmark.sh

@@ -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
@@ -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
 
 }

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
 }
@@ -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
 }

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}"

benchmarks/kernels/benchmark_moe.py

@@ -22,6 +22,13 @@ 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
@@ -570,12 +577,10 @@ 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 +589,14 @@ 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 +604,14 @@ 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"
@@ -735,6 +743,7 @@ 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"
     )

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)

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

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}")

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,
+                    )

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)

benchmarks/kernels/benchmark_trtllm_decode_attention.py

@@ -41,7 +41,6 @@ def benchmark_decode(
     device = "cuda"
     torch.manual_seed(0)
 
-    # Currently only HEAD_GRP_SIZE == 8 is supported
     HEAD_GRP_SIZE = 8
     MAX_SEQ_LEN = max_seq_len
 
@@ -71,22 +70,20 @@ def benchmark_decode(
     if kv_cache_dtype.startswith("fp8"):
         kv_cache, _ = to_float8(kv_cache)
 
+    output_trtllm = torch.empty(q.shape, dtype=dtype)
+
     # 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,
+            bmm1_scale=k_scale * sm_scale,
+            bmm2_scale=v_scale,
+            out=output_trtllm,
         )
 
     def time_fn(fn, warmup=10, trials=20):
@@ -125,6 +122,8 @@ def benchmark_decode(
     kv_indices = torch.tensor(kv_indices, dtype=torch.int32)
     kv_last_page_lens = torch.tensor(kv_last_page_lens, dtype=torch.int32)
 
+    output_baseline = torch.empty(q.shape, dtype=dtype)
+
     wrapper = flashinfer.BatchDecodeWithPagedKVCacheWrapper(
         workspace_buffer,
         kv_layout,
@@ -145,7 +144,7 @@ def benchmark_decode(
     )
 
     def baseline_decode():
-        return wrapper.run(q, kv_cache, sm_scale, k_scale, v_scale)
+        return wrapper.run(q, kv_cache, sm_scale, k_scale, v_scale, output_baseline)
 
     baseline_mean, baseline_std = time_fn(baseline_decode)
 
@@ -214,25 +213,39 @@ if __name__ == "__main__":
     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"
+        "Running benchmark for q_dtype = bfloat16, kv_cache_dtype: bfloat16, "
+        "output_dtype: bfloat16"
+    )
+    print(
+        "\tnum_seqs\tmax_seq_len\ttrt_mean\ttrt_std\tbaseline_mean\t"
+        "baseline_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"
+                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"
+        "Running benchmark for q_dtype = bfloat16, kv_cache_dtype: fp8, "
+        "output_dtype: bfloat16"
+    )
+    print(
+        "\tnum_seqs\tmax_seq_len\ttrt_mean\ttrt_std\tbaseline_mean\t"
+        "baseline_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"
+                bs,
+                max_seq_len,
+                dtype=torch.bfloat16,
+                kv_cache_dtype="fp8",
             )
             all_results.append(result)
 

benchmarks/kernels/benchmark_trtllm_prefill_attention.py

@@ -0,0 +1,250 @@
+# 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_prefill(
+    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")
+    torch.manual_seed(0)
+
+    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)
+
+    num_qo_heads = num_kv_heads * HEAD_GRP_SIZE
+    sm_scale = float(1.0 / (head_dim**0.5))
+
+    q_lens = [random.randint(1, MAX_SEQ_LEN) for _ in range(num_seqs)]
+    q_lens[-1] = MAX_SEQ_LEN
+    max_q_len = max(q_lens)
+    q_indptr = torch.cat(
+        [
+            torch.tensor([0], dtype=torch.int32),
+            torch.cumsum(
+                torch.tensor(q_lens, dtype=torch.int32), dim=0, dtype=torch.int32
+            ),
+        ]
+    )
+    q = torch.randn(sum(q_lens), num_qo_heads, head_dim, dtype=dtype)
+
+    kv_lens = [random.randint(0, MAX_SEQ_LEN) for _ in range(num_seqs)]
+    kv_lens[-1] = MAX_SEQ_LEN
+
+    seq_lens = [q_len + kv_len for q_len, kv_len in zip(q_lens, kv_lens)]
+    max_seq_len = max(seq_lens)
+    seq_lens_tensor = torch.tensor(seq_lens, dtype=torch.int32)
+
+    max_num_blocks_per_seq = (max_seq_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, dtype=dtype)
+    k_scale = v_scale = 1.0
+
+    if kv_cache_dtype.startswith("fp8"):
+        kv_cache, _ = to_float8(kv_cache)
+
+    output_trtllm = torch.empty(q.shape, dtype=dtype)
+
+    kv_indptr = [0]
+    kv_indices = []
+    kv_last_page_lens = []
+    for i in range(num_seqs):
+        seq_len = seq_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)
+
+    output_baseline = torch.empty(q.shape, dtype=dtype)
+
+    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_dim,
+        page_size,
+        causal=True,
+        sm_scale=sm_scale,
+        q_data_type=dtype,
+        kv_data_type=kv_cache.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))
+
+    def baseline_prefill():
+        return wrapper.run(
+            q, kv_cache, k_scale=k_scale, v_scale=v_scale, out=output_baseline
+        )
+
+    def trt_prefill():
+        return flashinfer.prefill.trtllm_batch_context_with_kv_cache(
+            query=q,
+            kv_cache=kv_cache,
+            workspace_buffer=workspace_buffer,
+            block_tables=block_tables,
+            seq_lens=seq_lens_tensor,
+            max_q_len=max_q_len,
+            max_kv_len=max_seq_len,
+            bmm1_scale=k_scale * sm_scale,
+            bmm2_scale=v_scale,
+            batch_size=num_seqs,
+            cum_seq_lens_q=q_indptr,
+            cum_seq_lens_kv=kv_indptr,
+            out=output_trtllm,
+        )
+
+    trt_mean, trt_std = time_fn(trt_prefill)
+    baseline_mean, baseline_std = time_fn(baseline_prefill)
+
+    # 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:.5f}\t{trt_std.item():.5f}"
+        f"\t{baseline_mean:.5f}\t{baseline_std.item():.5f}\t{speedup_percent:.5f}"
+    )
+
+    # 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 q_dtype = bfloat16, kv_cache_dtype: bfloat16, "
+        "output_dtype: bfloat16"
+    )
+    print(
+        "\tnum_seqs\tmax_seq_len\ttrt_mean\ttrt_std\tbaseline_mean\t"
+        "baseline_std\tspeedup_percent"
+    )
+    for max_seq_len in max_seq_lens:
+        for bs in num_seqs:
+            result = benchmark_prefill(
+                bs,
+                max_seq_len,
+                dtype=torch.bfloat16,
+                kv_cache_dtype="auto",
+            )
+            all_results.append(result)
+
+    # Write all results to CSV
+    write_results_to_csv(all_results)

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 =====

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

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

benchmarks/multi_turn/README.md

@@ -0,0 +1,71 @@
+# 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_NAME=/models/meta-llama/Meta-Llama-3.1-8B-Instruct/
+
+vllm serve $MODEL_NAME --disable-log-requests
+```
+
+## 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_NAME=/models/meta-llama/Meta-Llama-3.1-8B-Instruct/
+
+python benchmark_serving_multi_turn.py --model $MODEL_NAME --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`.

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

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__)

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()

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
+        }
+    }
+}

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

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

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

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 93cf5a08f421a3efd0c4a7e005ef8f742b578ce0
           GIT_PROGRESS TRUE
           # Don't share the vllm-flash-attn build between build types
           BINARY_DIR ${CMAKE_BINARY_DIR}/vllm-flash-attn

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})
 

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>

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);

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);

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);
     }
   }
 }

csrc/cpu/quant.cpp

@@ -16,12 +16,14 @@ struct KernelVecType<float> {
   using cvt_vec_type = vec_op::FP32Vec16;
 };
 
+#if !defined(__aarch64__) || defined(ARM_BF16_SUPPORT)
 template <>
 struct KernelVecType<c10::BFloat16> {
   using load_vec_type = vec_op::BF16Vec16;
   using azp_adj_load_vec_type = vec_op::INT32Vec16;
   using cvt_vec_type = vec_op::FP32Vec16;
 };
+#endif
 
 template <>
 struct KernelVecType<c10::Half> {

csrc/cpu/torch_bindings.cpp

@@ -151,7 +151,7 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, ops) {
   ops.impl("rotary_embedding", torch::kCPU, &rotary_embedding);
 
   // Quantization
-#if defined(__AVX512F__) || defined(__aarch64__)
+#if defined(__AVX512F__) || (defined(__aarch64__) && !defined(__APPLE__))
   at::Tag stride_tag = at::Tag::needs_fixed_stride_order;
 
   // Compute int8 quantized tensor for given scaling factor.

csrc/cuda_compat.h

@@ -4,8 +4,35 @@
   #include <hip/hip_runtime.h>
 #endif
 
-#if defined(USE_ROCM) && defined(__GFX9__)
-  #define WARP_SIZE 64
+#ifdef USE_ROCM
+struct Utils {
+  static __host__ int get_warp_size() {
+    static bool is_cached = false;
+    static int result;
+
+    if (!is_cached) {
+      int device_id;
+      cudaDeviceProp deviceProp;
+      cudaGetDevice(&device_id);
+      cudaGetDeviceProperties(&deviceProp, device_id);
+
+      result = deviceProp.warpSize;
+      is_cached = true;
+    }
+
+    return result;
+  }
+
+  static __device__ constexpr int get_warp_size() {
+  #ifdef __GFX9__
+    return 64;
+  #else
+    return 32;
+  #endif
+  }
+};
+
+  #define WARP_SIZE Utils::get_warp_size()
 #else
   #define WARP_SIZE 32
 #endif

csrc/cutlass_extensions/common.hpp

@@ -60,3 +60,13 @@ struct enable_sm100_only : Kernel {
 #endif
   }
 };
+
+template <typename Kernel>
+struct enable_sm120_only : Kernel {
+  template <typename... Args>
+  CUTLASS_DEVICE void operator()(Args&&... args) {
+#if defined __CUDA_ARCH__ && __CUDA_ARCH__ == 1200
+    Kernel::operator()(std::forward<Args>(args)...);
+#endif
+  }
+};

csrc/mamba/mamba_ssm/selective_scan.h

@@ -45,6 +45,9 @@ struct SSMParamsBase {
     index_t out_d_stride;
     index_t out_z_batch_stride;
     index_t out_z_d_stride;
+    index_t ssm_states_batch_stride;
+    index_t ssm_states_dim_stride;  
+    index_t ssm_states_dstate_stride;
 
     // Common data pointers.
     void *__restrict__ A_ptr;

csrc/mamba/mamba_ssm/selective_scan_fwd.cu

@@ -132,7 +132,9 @@ void selective_scan_fwd_kernel(SSMParamsBase params) {
     input_t *Bvar = reinterpret_cast<input_t *>(params.B_ptr) + sequence_start_index * params.B_batch_stride + group_id * params.B_group_stride;
     weight_t *C = reinterpret_cast<weight_t *>(params.C_ptr) + dim_id * kNRows * params.C_d_stride;
     input_t *Cvar = reinterpret_cast<input_t *>(params.C_ptr) + sequence_start_index * params.C_batch_stride + group_id * params.C_group_stride;
-    input_t *ssm_states = reinterpret_cast<input_t *>(params.ssm_states_ptr) + (cache_index * params.dim + dim_id * kNRows) * params.dstate;
+    input_t *ssm_states = reinterpret_cast<input_t *>(params.ssm_states_ptr) + 
+    cache_index * params.ssm_states_batch_stride + 
+    dim_id * kNRows * params.ssm_states_dim_stride;
     
     float D_val[kNRows] = {0};
     if (params.D_ptr != nullptr) {
@@ -248,7 +250,7 @@ void selective_scan_fwd_kernel(SSMParamsBase params) {
                 }
                 // Initialize running total
 
-                scan_t running_prefix = chunk > 0 ? smem_running_prefix[state_idx + r * MAX_DSTATE] : make_float2(1.0, has_initial_state ? float(ssm_states[state_idx]): 0.0);
+                scan_t running_prefix = chunk > 0 ? smem_running_prefix[state_idx + r * MAX_DSTATE] : make_float2(1.0, has_initial_state ? float(ssm_states[state_idx * params.ssm_states_dstate_stride]): 0.0);
 
                 SSMScanPrefixCallbackOp<weight_t> prefix_op(running_prefix);
                 typename Ktraits::BlockScanT(smem_scan).InclusiveScan(
@@ -259,7 +261,7 @@ void selective_scan_fwd_kernel(SSMParamsBase params) {
                 if (threadIdx.x == 0) {
                     smem_running_prefix[state_idx] = prefix_op.running_prefix;
                     if (chunk == n_chunks - 1) {
-                        ssm_states[state_idx] = input_t(prefix_op.running_prefix.y);
+                        ssm_states[state_idx * params.ssm_states_dstate_stride] = input_t(prefix_op.running_prefix.y);
                     }
                 }
                 #pragma unroll
@@ -481,6 +483,10 @@ void set_ssm_params_fwd(SSMParamsBase &params,
         params.out_batch_stride = out.stride(1);
         params.out_d_stride = out.stride(0);
 
+        params.ssm_states_batch_stride = ssm_states.stride(0);
+        params.ssm_states_dim_stride = ssm_states.stride(1);  
+        params.ssm_states_dstate_stride = ssm_states.stride(2);
+
     }
     else{
         if (!is_variable_B) {
@@ -509,6 +515,10 @@ void set_ssm_params_fwd(SSMParamsBase &params,
         }
         params.out_batch_stride = out.stride(0);
         params.out_d_stride = out.stride(1);
+        
+        params.ssm_states_batch_stride = ssm_states.stride(0);
+        params.ssm_states_dim_stride = ssm_states.stride(1);  
+        params.ssm_states_dstate_stride = ssm_states.stride(2);
     }
 }
 

csrc/moe/moe_permute_unpermute_op.cu

@@ -10,32 +10,28 @@
 
 void moe_permute(
     const torch::Tensor& input,                      // [n_token, hidden]
-    const torch::Tensor& topk_weights,               //[n_token, topk]
-    torch::Tensor& topk_ids,                         // [n_token, topk]
+    const torch::Tensor& topk_ids,                   // [n_token, topk]
     const torch::Tensor& token_expert_indices,       // [n_token, topk]
     const std::optional<torch::Tensor>& expert_map,  // [n_expert]
     int64_t n_expert, int64_t n_local_expert, int64_t topk,
     const std::optional<int64_t>& align_block_size,
-    torch::Tensor&
-        permuted_input,  // [topk * n_token/align_block_size_m, hidden]
+    torch::Tensor& permuted_input,             // [permuted_size, hidden]
     torch::Tensor& expert_first_token_offset,  // [n_local_expert + 1]
-    torch::Tensor& src_row_id2dst_row_id_map,  // [n_token, topk]
+    torch::Tensor& inv_permuted_idx,           // [n_token, topk]
+    torch::Tensor& permuted_idx,               // [permute_size]
     torch::Tensor& m_indices) {                // [align_expand_m]
-  TORCH_CHECK(topk_weights.scalar_type() == at::ScalarType::Float,
-              "topk_weights must be float32");
   TORCH_CHECK(expert_first_token_offset.scalar_type() == at::ScalarType::Long,
               "expert_first_token_offset must be int64");
   TORCH_CHECK(topk_ids.scalar_type() == at::ScalarType::Int,
               "topk_ids must be int32");
   TORCH_CHECK(token_expert_indices.scalar_type() == at::ScalarType::Int,
               "token_expert_indices must be int32");
-  TORCH_CHECK(src_row_id2dst_row_id_map.scalar_type() == at::ScalarType::Int,
-              "src_row_id2dst_row_id_map must be int32");
+  TORCH_CHECK(inv_permuted_idx.scalar_type() == at::ScalarType::Int,
+              "inv_permuted_idx must be int32");
   TORCH_CHECK(expert_first_token_offset.size(0) == n_local_expert + 1,
               "expert_first_token_offset shape != n_local_expert+1")
-  TORCH_CHECK(
-      src_row_id2dst_row_id_map.sizes() == token_expert_indices.sizes(),
-      "token_expert_indices shape must be same as src_row_id2dst_row_id_map");
+  TORCH_CHECK(inv_permuted_idx.sizes() == token_expert_indices.sizes(),
+              "token_expert_indices shape must be same as inv_permuted_idx");
   auto n_token = input.sizes()[0];
   auto n_hidden = input.sizes()[1];
   auto align_block_size_value =
@@ -46,8 +42,9 @@ void moe_permute(
   auto sort_workspace = torch::empty(
       {sorter_size},
       torch::dtype(torch::kInt8).device(torch::kCUDA).requires_grad(false));
+  auto copy_topk_ids = topk_ids.clone();  // copy topk_ids for preprocess
   auto permuted_experts_id = torch::empty_like(topk_ids);
-  auto dst_row_id2src_row_id_map = torch::empty_like(src_row_id2dst_row_id_map);
+  auto sorted_row_idx = torch::empty_like(inv_permuted_idx);
   auto align_expert_first_token_offset =
       torch::zeros_like(expert_first_token_offset);
 
@@ -67,24 +64,22 @@ void moe_permute(
     const int* expert_map_ptr = get_ptr<int>(expert_map.value());
     valid_num_ptr =
         get_ptr<int64_t>(expert_first_token_offset) + n_local_expert;
-    preprocessTopkIdLauncher(get_ptr<int>(topk_ids), n_token * topk,
+    preprocessTopkIdLauncher(get_ptr<int>(copy_topk_ids), n_token * topk,
                              expert_map_ptr, n_expert, stream);
   }
   // expert sort topk expert id and scan expert id get expert_first_token_offset
-  sortAndScanExpert(get_ptr<int>(topk_ids), get_ptr<int>(token_expert_indices),
-                    get_ptr<int>(permuted_experts_id),
-                    get_ptr<int>(dst_row_id2src_row_id_map),
-                    get_ptr<int64_t>(expert_first_token_offset), n_token,
-                    n_expert, n_local_expert, topk, sorter,
-                    get_ptr<int>(sort_workspace), stream);
+  sortAndScanExpert(
+      get_ptr<int>(copy_topk_ids), get_ptr<int>(token_expert_indices),
+      get_ptr<int>(permuted_experts_id), get_ptr<int>(sorted_row_idx),
+      get_ptr<int64_t>(expert_first_token_offset), n_token, n_expert,
+      n_local_expert, topk, sorter, get_ptr<int>(sort_workspace), stream);
 
   // dispatch expandInputRowsKernelLauncher
   MOE_DISPATCH(input.scalar_type(), [&] {
     expandInputRowsKernelLauncher<scalar_t>(
         get_ptr<scalar_t>(input), get_ptr<scalar_t>(permuted_input),
-        get_ptr<float>(topk_weights), get_ptr<int>(permuted_experts_id),
-        get_ptr<int>(dst_row_id2src_row_id_map),
-        get_ptr<int>(src_row_id2dst_row_id_map),
+        get_ptr<int>(permuted_experts_id), get_ptr<int>(sorted_row_idx),
+        get_ptr<int>(inv_permuted_idx), get_ptr<int>(permuted_idx),
         get_ptr<int64_t>(expert_first_token_offset), n_token, valid_num_ptr,
         n_hidden, topk, n_local_expert, align_block_size_value, stream);
   });
@@ -101,32 +96,34 @@ void moe_permute(
 }
 
 void moe_unpermute(
-    const torch::Tensor& permuted_hidden_states,     // [n_token * topk, hidden]
-    const torch::Tensor& topk_weights,               //[n_token, topk]
-    const torch::Tensor& topk_ids,                   // [n_token, topk]
-    const torch::Tensor& src_row_id2dst_row_id_map,  // [n_token, topk]
-    const torch::Tensor& expert_first_token_offset,  // [n_local_expert+1]
-    int64_t n_expert, int64_t n_local_expert, int64_t topk,
+    const torch::Tensor& permuted_hidden_states,  // [n_token * topk, hidden]
+    const torch::Tensor& topk_weights,            // [n_token, topk]
+    const torch::Tensor& inv_permuted_idx,        // [n_token, topk]
+    const std::optional<torch::Tensor>&
+        expert_first_token_offset,  // [n_local_expert+1]
+    int64_t topk,
     torch::Tensor& hidden_states  // [n_token, hidden]
 ) {
-  TORCH_CHECK(src_row_id2dst_row_id_map.sizes() == topk_ids.sizes(),
-              "topk_ids shape must be same as src_row_id2dst_row_id_map");
-  TORCH_CHECK(topk_ids.scalar_type() == at::ScalarType::Int,
-              "topk_ids must be int32");
   TORCH_CHECK(
       permuted_hidden_states.scalar_type() == hidden_states.scalar_type(),
-      "topk_ids dtype must be same as src_row_id2dst_row_id_map");
+      "permuted_hidden_states dtype must be same as hidden_states");
   auto n_token = hidden_states.size(0);
   auto n_hidden = hidden_states.size(1);
   auto stream = at::cuda::getCurrentCUDAStream().stream();
-  const int64_t* valid_ptr =
-      get_ptr<int64_t>(expert_first_token_offset) + n_local_expert;
+
+  int64_t const* valid_ptr = nullptr;
+  if (expert_first_token_offset.has_value()) {
+    int n_local_expert = expert_first_token_offset.value().size(0) - 1;
+    valid_ptr =
+        get_ptr<int64_t>(expert_first_token_offset.value()) + n_local_expert;
+  }
+
   MOE_DISPATCH(hidden_states.scalar_type(), [&] {
     finalizeMoeRoutingKernelLauncher<scalar_t, scalar_t>(
         get_ptr<scalar_t>(permuted_hidden_states),
         get_ptr<scalar_t>(hidden_states), get_ptr<float>(topk_weights),
-        get_ptr<int>(src_row_id2dst_row_id_map), get_ptr<int>(topk_ids),
-        n_token, n_hidden, topk, valid_ptr, stream);
+        get_ptr<int>(inv_permuted_idx), n_token, n_hidden, topk, valid_ptr,
+        stream);
   });
 }
 

csrc/moe/permute_unpermute_kernels/moe_permute_unpermute_kernel.cu

@@ -177,7 +177,7 @@ __global__ void getMIndicesKernel(int64_t* expert_first_token_offset,
   int tidx = threadIdx.x;
   extern __shared__ int64_t smem_expert_first_token_offset[];
   for (int i = tidx; i <= num_local_expert; i += blockDim.x) {
-    smem_expert_first_token_offset[tidx] = __ldg(expert_first_token_offset + i);
+    smem_expert_first_token_offset[i] = __ldg(expert_first_token_offset + i);
   }
   __syncthreads();
   auto last_token_offset = smem_expert_first_token_offset[eidx + 1];

csrc/moe/permute_unpermute_kernels/moe_permute_unpermute_kernel.h

@@ -57,31 +57,19 @@ void sortAndScanExpert(int* expert_for_source_row, const int* source_rows,
 
 template <typename T>
 void expandInputRowsKernelLauncher(
-    T const* unpermuted_input, T* permuted_output,
-    const float* unpermuted_scales, int* sorted_experts,
+    T const* unpermuted_input, T* permuted_output, int* sorted_experts,
     int const* expanded_dest_row_to_expanded_source_row,
-    int* expanded_source_row_to_expanded_dest_row,
+    int* expanded_source_row_to_expanded_dest_row, int* permuted_idx,
     int64_t* expert_first_token_offset, int64_t const num_rows,
     int64_t const* num_valid_tokens_ptr, int64_t const cols, int const k,
     int num_local_experts, const int& align_block_size, cudaStream_t stream);
 
-// Final kernel to unpermute and scale
-// This kernel unpermutes the original data, does the k-way reduction and
-// performs the final skip connection.
-template <typename T, typename OutputType, bool CHECK_SKIPPED>
-__global__ void finalizeMoeRoutingKernel(
-    T const* expanded_permuted_rows, OutputType* reduced_unpermuted_output,
-    float const* scales, int const* expanded_source_row_to_expanded_dest_row,
-    int const* expert_for_source_row, int64_t const orig_cols, int64_t const k,
-    int64_t const* num_valid_ptr);
-
 template <class T, class OutputType>
 void finalizeMoeRoutingKernelLauncher(
     T const* expanded_permuted_rows, OutputType* reduced_unpermuted_output,
     float const* scales, int const* expanded_source_row_to_expanded_dest_row,
-    int const* expert_for_source_row, int64_t const num_rows,
-    int64_t const cols, int64_t const k, int64_t const* num_valid_ptr,
-    cudaStream_t stream);
+    int64_t const num_rows, int64_t const cols, int64_t const k,
+    int64_t const* num_valid_ptr, cudaStream_t stream);
 
 void preprocessTopkIdLauncher(int* topk_id_ptr, int size,
                               const int* expert_map_ptr, int num_experts,

csrc/moe/permute_unpermute_kernels/moe_permute_unpermute_kernel.inl

@@ -2,10 +2,9 @@
 
 template <typename T, bool CHECK_SKIPPED, bool ALIGN_BLOCK_SIZE>
 __global__ void expandInputRowsKernel(
-    T const* unpermuted_input, T* permuted_output,
-    const float* unpermuted_scales, int* sorted_experts,
+    T const* unpermuted_input, T* permuted_output, int* sorted_experts,
     int const* expanded_dest_row_to_expanded_source_row,
-    int* expanded_source_row_to_expanded_dest_row,
+    int* expanded_source_row_to_expanded_dest_row, int* permuted_idx,
     int64_t* expert_first_token_offset, int64_t const num_rows,
     int64_t const* num_dest_rows, int64_t const cols, int64_t k,
     int num_local_experts, int align_block_size) {
@@ -54,6 +53,10 @@ __global__ void expandInputRowsKernel(
     assert(expanded_dest_row <= INT32_MAX);
     expanded_source_row_to_expanded_dest_row[expanded_source_row] =
         static_cast<int>(expanded_dest_row);
+    // skip non local expert token
+    if (!CHECK_SKIPPED || blockIdx.x < *num_dest_rows) {
+      permuted_idx[expanded_dest_row] = expanded_source_row;
+    }
   }
 
   if (!CHECK_SKIPPED || blockIdx.x < *num_dest_rows) {
@@ -62,7 +65,7 @@ __global__ void expandInputRowsKernel(
     using DataElem = cutlass::Array<T, ELEM_PER_THREAD>;
 
     // Duplicate and permute rows
-    int64_t const source_row = expanded_source_row % num_rows;
+    int64_t const source_row = expanded_source_row / k;
 
     auto const* source_row_ptr =
         reinterpret_cast<DataElem const*>(unpermuted_input + source_row * cols);
@@ -82,10 +85,9 @@ __global__ void expandInputRowsKernel(
 
 template <typename T>
 void expandInputRowsKernelLauncher(
-    T const* unpermuted_input, T* permuted_output,
-    const float* unpermuted_scales, int* sorted_experts,
+    T const* unpermuted_input, T* permuted_output, int* sorted_experts,
     int const* expanded_dest_row_to_expanded_source_row,
-    int* expanded_source_row_to_expanded_dest_row,
+    int* expanded_source_row_to_expanded_dest_row, int* permuted_idx,
     int64_t* expert_first_token_offset, int64_t const num_rows,
     int64_t const* num_valid_tokens_ptr, int64_t const cols, int const k,
     int num_local_experts, const int& align_block_size, cudaStream_t stream) {
@@ -105,11 +107,11 @@ void expandInputRowsKernelLauncher(
   int64_t smem_size = sizeof(int64_t) * (num_local_experts + 1);
 
   func<<<blocks, threads, smem_size, stream>>>(
-      unpermuted_input, permuted_output, unpermuted_scales, sorted_experts,
+      unpermuted_input, permuted_output, sorted_experts,
       expanded_dest_row_to_expanded_source_row,
-      expanded_source_row_to_expanded_dest_row, expert_first_token_offset,
-      num_rows, num_valid_tokens_ptr, cols, k, num_local_experts,
-      align_block_size);
+      expanded_source_row_to_expanded_dest_row, permuted_idx,
+      expert_first_token_offset, num_rows, num_valid_tokens_ptr, cols, k,
+      num_local_experts, align_block_size);
 }
 
 template <class T, class U>
@@ -128,11 +130,9 @@ template <typename T, typename OutputType, bool CHECK_SKIPPED>
 __global__ void finalizeMoeRoutingKernel(
     T const* expanded_permuted_rows, OutputType* reduced_unpermuted_output,
     float const* scales, int const* expanded_source_row_to_expanded_dest_row,
-    int const* expert_for_source_row, int64_t const orig_cols, int64_t const k,
-    int64_t const* num_valid_ptr) {
+    int64_t const orig_cols, int64_t const k, int64_t const* num_valid_ptr) {
   assert(orig_cols % 4 == 0);
   int64_t const original_row = blockIdx.x;
-  int64_t const num_rows = gridDim.x;
   auto const offset = original_row * orig_cols;
   OutputType* reduced_row_ptr = reduced_unpermuted_output + offset;
   int64_t const num_valid = *num_valid_ptr;
@@ -159,14 +159,13 @@ __global__ void finalizeMoeRoutingKernel(
     ComputeElem thread_output;
     thread_output.fill(0);
     for (int k_idx = 0; k_idx < k; ++k_idx) {
-      int64_t const expanded_original_row = original_row + k_idx * num_rows;
+      int64_t const expanded_original_row = original_row * k + k_idx;
       int64_t const expanded_permuted_row =
           expanded_source_row_to_expanded_dest_row[expanded_original_row];
 
       int64_t const k_offset = original_row * k + k_idx;
       float const row_scale = scales[k_offset];
 
-      // Check after row_rescale has accumulated
       if (CHECK_SKIPPED && expanded_permuted_row >= num_valid) {
         continue;
       }
@@ -189,9 +188,8 @@ template <class T, class OutputType>
 void finalizeMoeRoutingKernelLauncher(
     T const* expanded_permuted_rows, OutputType* reduced_unpermuted_output,
     float const* scales, int const* expanded_source_row_to_expanded_dest_row,
-    int const* expert_for_source_row, int64_t const num_rows,
-    int64_t const cols, int64_t const k, int64_t const* num_valid_ptr,
-    cudaStream_t stream) {
+    int64_t const num_rows, int64_t const cols, int64_t const k,
+    int64_t const* num_valid_ptr, cudaStream_t stream) {
   int64_t const blocks = num_rows;
   int64_t const threads = 256;
   bool const check_finished = num_valid_ptr != nullptr;
@@ -201,6 +199,5 @@ void finalizeMoeRoutingKernelLauncher(
   auto* const kernel = func_map[check_finished];
   kernel<<<blocks, threads, 0, stream>>>(
       expanded_permuted_rows, reduced_unpermuted_output, scales,
-      expanded_source_row_to_expanded_dest_row, expert_for_source_row, cols, k,
-      num_valid_ptr);
+      expanded_source_row_to_expanded_dest_row, cols, k, num_valid_ptr);
 }

csrc/moe/topk_softmax_kernels.cu

@@ -24,9 +24,12 @@
 #ifndef USE_ROCM
     #include <cub/util_type.cuh>
     #include <cub/cub.cuh>
+    #include <cuda/std/functional>
+    using AddOp = cuda::std::plus<float>;
 #else
     #include <hipcub/util_type.hpp>
     #include <hipcub/hipcub.hpp>
+    using AddOp = cub::Sum; 
 #endif
 
 #define MAX(a, b) ((a) > (b) ? (a) : (b))
@@ -62,7 +65,6 @@ __launch_bounds__(TPB) __global__
 
     const int thread_row_offset = blockIdx.x * num_cols;
 
-    cub::Sum sum;
     float threadData(-FLT_MAX);
 
     // Don't touch finished rows.
@@ -92,7 +94,7 @@ __launch_bounds__(TPB) __global__
         threadData += exp((static_cast<float>(input[idx]) - float_max));
     }
 
-    const auto Z = BlockReduce(tmpStorage).Reduce(threadData, sum);
+    const auto Z = BlockReduce(tmpStorage).Reduce(threadData, AddOp());
 
     if (threadIdx.x == 0)
     {
@@ -186,18 +188,18 @@ __launch_bounds__(TPB) __global__ void moeTopK(
   It fuses the softmax, max and argmax into a single kernel.
 
   Limitations:
-  1) This implementation is intended for when the number of experts is a small power of 2.
+  1) This implementation is optimized for when the number of experts is a small power of 2.
+     Additionally it also supports when number of experts is multiple of 64 which is still
+     faster than the computing softmax and topK separately (only tested on CUDA yet).
   2) This implementation assumes k is small, but will work for any k.
 */
 
-template <int VPT, int NUM_EXPERTS, int WARPS_PER_CTA, int BYTES_PER_LDG, typename IndType>
-__launch_bounds__(WARPS_PER_CTA* WARP_SIZE) __global__
+template <int VPT, int NUM_EXPERTS, int WARPS_PER_CTA, int BYTES_PER_LDG, int WARP_SIZE_PARAM, typename IndType>
+__launch_bounds__(WARPS_PER_CTA* WARP_SIZE_PARAM) __global__
     void topkGatingSoftmax(const float* input, const bool* finished, float* output, const int num_rows, IndType* indices,
         int* source_rows, const int k, const int start_expert, const int end_expert)
 {
     // We begin by enforcing compile time assertions and setting up compile time constants.
-    static_assert(VPT == (VPT & -VPT), "VPT must be power of 2");
-    static_assert(NUM_EXPERTS == (NUM_EXPERTS & -NUM_EXPERTS), "NUM_EXPERTS must be power of 2");
     static_assert(BYTES_PER_LDG == (BYTES_PER_LDG & -BYTES_PER_LDG), "BYTES_PER_LDG must be power of 2");
     static_assert(BYTES_PER_LDG <= 16, "BYTES_PER_LDG must be leq 16");
 
@@ -209,12 +211,12 @@ __launch_bounds__(WARPS_PER_CTA* WARP_SIZE) __global__
 
     // Restrictions based on previous section.
     static_assert(VPT % ELTS_PER_LDG == 0, "The elements per thread must be a multiple of the elements per ldg");
-    static_assert(WARP_SIZE % THREADS_PER_ROW == 0, "The threads per row must cleanly divide the threads per warp");
+    static_assert(WARP_SIZE_PARAM % THREADS_PER_ROW == 0, "The threads per row must cleanly divide the threads per warp");
     static_assert(THREADS_PER_ROW == (THREADS_PER_ROW & -THREADS_PER_ROW), "THREADS_PER_ROW must be power of 2");
-    static_assert(THREADS_PER_ROW <= WARP_SIZE, "THREADS_PER_ROW can be at most warp size");
+    static_assert(THREADS_PER_ROW <= WARP_SIZE_PARAM, "THREADS_PER_ROW can be at most warp size");
 
     // We have NUM_EXPERTS elements per row. We specialize for small #experts
-    static constexpr int ELTS_PER_WARP = WARP_SIZE * VPT;
+    static constexpr int ELTS_PER_WARP = WARP_SIZE_PARAM * VPT;
     static constexpr int ROWS_PER_WARP = ELTS_PER_WARP / ELTS_PER_ROW;
     static constexpr int ROWS_PER_CTA = WARPS_PER_CTA * ROWS_PER_WARP;
 
@@ -393,41 +395,55 @@ __launch_bounds__(WARPS_PER_CTA* WARP_SIZE) __global__
 namespace detail
 {
 // Constructs some constants needed to partition the work across threads at compile time.
-template <int EXPERTS, int BYTES_PER_LDG>
+template <int EXPERTS, int BYTES_PER_LDG, int WARP_SIZE_PARAM>
 struct TopkConstants
 {
     static constexpr int ELTS_PER_LDG = BYTES_PER_LDG / sizeof(float);
-    static_assert(EXPERTS / (ELTS_PER_LDG * WARP_SIZE) == 0 || EXPERTS % (ELTS_PER_LDG * WARP_SIZE) == 0, "");
-    static constexpr int VECs_PER_THREAD = MAX(1, EXPERTS / (ELTS_PER_LDG * WARP_SIZE));
+    static_assert(EXPERTS / (ELTS_PER_LDG * WARP_SIZE_PARAM) == 0 || EXPERTS % (ELTS_PER_LDG * WARP_SIZE_PARAM) == 0, "");
+    static constexpr int VECs_PER_THREAD = MAX(1, EXPERTS / (ELTS_PER_LDG * WARP_SIZE_PARAM));
     static constexpr int VPT = VECs_PER_THREAD * ELTS_PER_LDG;
     static constexpr int THREADS_PER_ROW = EXPERTS / VPT;
-    static constexpr int ROWS_PER_WARP = WARP_SIZE / THREADS_PER_ROW;
+    static const int ROWS_PER_WARP = WARP_SIZE_PARAM / THREADS_PER_ROW;
 };
 } // namespace detail
 
-template <int EXPERTS, int WARPS_PER_TB, typename IndType>
+template <int EXPERTS, int WARPS_PER_TB, int WARP_SIZE_PARAM, int MAX_BYTES_PER_LDG, typename IndType>
 void topkGatingSoftmaxLauncherHelper(const float* input, const bool* finished, float* output, IndType* indices,
     int* source_row, const int num_rows, const int k, const int start_expert, const int end_expert, cudaStream_t stream)
 {
-    static constexpr std::size_t MAX_BYTES_PER_LDG = 16;
-
     static constexpr int BYTES_PER_LDG = MIN(MAX_BYTES_PER_LDG, sizeof(float) * EXPERTS);
-    using Constants = detail::TopkConstants<EXPERTS, BYTES_PER_LDG>;
+    using Constants = detail::TopkConstants<EXPERTS, BYTES_PER_LDG, WARP_SIZE_PARAM>;
     static constexpr int VPT = Constants::VPT;
     static constexpr int ROWS_PER_WARP = Constants::ROWS_PER_WARP;
     const int num_warps = (num_rows + ROWS_PER_WARP - 1) / ROWS_PER_WARP;
     const int num_blocks = (num_warps + WARPS_PER_TB - 1) / WARPS_PER_TB;
 
-    dim3 block_dim(WARP_SIZE, WARPS_PER_TB);
-    topkGatingSoftmax<VPT, EXPERTS, WARPS_PER_TB, BYTES_PER_LDG><<<num_blocks, block_dim, 0, stream>>>(
+    dim3 block_dim(WARP_SIZE_PARAM, WARPS_PER_TB);
+    topkGatingSoftmax<VPT, EXPERTS, WARPS_PER_TB, BYTES_PER_LDG, WARP_SIZE_PARAM><<<num_blocks, block_dim, 0, stream>>>(
         input, finished, output, num_rows, indices, source_row, k, start_expert, end_expert);
 }
 
-#define LAUNCH_SOFTMAX(NUM_EXPERTS, WARPS_PER_TB)                       \
-    topkGatingSoftmaxLauncherHelper<NUM_EXPERTS, WARPS_PER_TB>(         \
-        gating_output, nullptr, topk_weights, topk_indices,            \
-        token_expert_indices, num_tokens, topk, 0, num_experts,         \
-        stream);
+#ifndef USE_ROCM
+#define LAUNCH_SOFTMAX(NUM_EXPERTS, WARPS_PER_TB, MAX_BYTES)                          \
+    static_assert(WARP_SIZE == 32,                                                    \
+                  "Unsupported warp size. Only 32 is supported for CUDA");            \
+    topkGatingSoftmaxLauncherHelper<NUM_EXPERTS, WARPS_PER_TB, WARP_SIZE, MAX_BYTES>( \
+        gating_output, nullptr, topk_weights, topk_indices,                           \
+        token_expert_indices, num_tokens, topk, 0, num_experts, stream);
+#else
+#define LAUNCH_SOFTMAX(NUM_EXPERTS, WARPS_PER_TB, MAX_BYTES)                             \
+    if (WARP_SIZE == 64) {                                                               \
+        topkGatingSoftmaxLauncherHelper<NUM_EXPERTS, WARPS_PER_TB, 64, MAX_BYTES>(       \
+            gating_output, nullptr, topk_weights, topk_indices,                          \
+            token_expert_indices, num_tokens, topk, 0, num_experts, stream);             \
+    } else if (WARP_SIZE == 32) {                                                        \
+        topkGatingSoftmaxLauncherHelper<NUM_EXPERTS, WARPS_PER_TB, 32, MAX_BYTES>(       \
+            gating_output, nullptr, topk_weights, topk_indices,                          \
+            token_expert_indices, num_tokens, topk, 0, num_experts, stream);             \
+    } else {                                                                             \
+        assert(false && "Unsupported warp size. Only 32 and 64 are supported for ROCm"); \
+    }
+#endif
 
 template <typename IndType>
 void topkGatingSoftmaxKernelLauncher(
@@ -441,37 +457,64 @@ void topkGatingSoftmaxKernelLauncher(
     const int topk,
     cudaStream_t stream) {
     static constexpr int WARPS_PER_TB = 4;
+    static constexpr int BYTES_PER_LDG_POWER_OF_2 = 16;
+#ifndef USE_ROCM
+    static constexpr int BYTES_PER_LDG_MULTIPLE_64 = 8;
+#endif
     switch (num_experts) {
         case 1:
-            LAUNCH_SOFTMAX(1, WARPS_PER_TB);
+            LAUNCH_SOFTMAX(1, WARPS_PER_TB, BYTES_PER_LDG_POWER_OF_2);
             break;
         case 2:
-            LAUNCH_SOFTMAX(2, WARPS_PER_TB);
+            LAUNCH_SOFTMAX(2, WARPS_PER_TB, BYTES_PER_LDG_POWER_OF_2);
             break;
         case 4:
-            LAUNCH_SOFTMAX(4, WARPS_PER_TB);
+            LAUNCH_SOFTMAX(4, WARPS_PER_TB, BYTES_PER_LDG_POWER_OF_2);
             break;
         case 8:
-            LAUNCH_SOFTMAX(8, WARPS_PER_TB);
+            LAUNCH_SOFTMAX(8, WARPS_PER_TB, BYTES_PER_LDG_POWER_OF_2);
             break;
         case 16:
-            LAUNCH_SOFTMAX(16, WARPS_PER_TB);
+            LAUNCH_SOFTMAX(16, WARPS_PER_TB, BYTES_PER_LDG_POWER_OF_2);
             break;
         case 32:
-            LAUNCH_SOFTMAX(32, WARPS_PER_TB);
+            LAUNCH_SOFTMAX(32, WARPS_PER_TB, BYTES_PER_LDG_POWER_OF_2);
             break;
         case 64:
-            LAUNCH_SOFTMAX(64, WARPS_PER_TB);
+            LAUNCH_SOFTMAX(64, WARPS_PER_TB, BYTES_PER_LDG_POWER_OF_2);
             break;
         case 128:
-            LAUNCH_SOFTMAX(128, WARPS_PER_TB);
+            LAUNCH_SOFTMAX(128, WARPS_PER_TB, BYTES_PER_LDG_POWER_OF_2);
             break;
         case 256:
-            LAUNCH_SOFTMAX(256, WARPS_PER_TB);
+            LAUNCH_SOFTMAX(256, WARPS_PER_TB, BYTES_PER_LDG_POWER_OF_2);
             break;
+        case 512:
+            LAUNCH_SOFTMAX(512, WARPS_PER_TB, BYTES_PER_LDG_POWER_OF_2);
+            break;
+        // (CUDA only) support multiples of 64 when num_experts is not power of 2.
+        // ROCm uses WARP_SIZE 64 so 8 bytes loading won't fit for some of num_experts,
+        // alternatively we can test 4 bytes loading and enable it in future.
+#ifndef USE_ROCM
+        case 192:
+            LAUNCH_SOFTMAX(192, WARPS_PER_TB, BYTES_PER_LDG_MULTIPLE_64);
+            break;
+        case 320:
+            LAUNCH_SOFTMAX(320, WARPS_PER_TB, BYTES_PER_LDG_MULTIPLE_64);
+            break;
+        case 384:
+            LAUNCH_SOFTMAX(384, WARPS_PER_TB, BYTES_PER_LDG_MULTIPLE_64);
+            break;
+        case 448:
+            LAUNCH_SOFTMAX(448, WARPS_PER_TB, BYTES_PER_LDG_MULTIPLE_64);
+            break;
+        case 576:
+            LAUNCH_SOFTMAX(576, WARPS_PER_TB, BYTES_PER_LDG_MULTIPLE_64);
+            break;
+#endif
         default: {
             TORCH_CHECK(softmax_workspace != nullptr,
-                "softmax_workspace must be provided for num_experts that are not a power of 2.");
+                "softmax_workspace must be provided for num_experts that are not a power of 2 or multiple of 64.");
             static constexpr int TPB = 256;
             moeSoftmax<TPB><<<num_tokens, TPB, 0, stream>>>(
                 gating_output, nullptr, softmax_workspace, num_experts);

csrc/moe/torch_bindings.cpp

@@ -56,18 +56,17 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, m) {
       " -> Tensor");
 
   m.def(
-      "moe_permute(Tensor input, Tensor topk_weight, Tensor! topk_ids,"
+      "moe_permute(Tensor input, Tensor topk_ids,"
       "Tensor token_expert_indices, Tensor? expert_map, int n_expert,"
       "int n_local_expert,"
       "int topk, int? align_block_size,Tensor! permuted_input, Tensor! "
-      "expert_first_token_offset, Tensor! src_row_id2dst_row_id_map, Tensor! "
-      "m_indices)->()");
+      "expert_first_token_offset, Tensor! inv_permuted_idx, Tensor! "
+      "permuted_idx, Tensor! m_indices)->()");
 
   m.def(
       "moe_unpermute(Tensor permuted_hidden_states, Tensor topk_weights,"
-      "Tensor topk_ids,Tensor src_row_id2dst_row_id_map, Tensor "
-      "expert_first_token_offset, int n_expert, int n_local_expert,int "
-      "topk, Tensor! hidden_states)->()");
+      "Tensor inv_permuted_idx, Tensor? expert_first_token_offset, "
+      "int topk, Tensor! hidden_states)->()");
 
   m.def("moe_permute_unpermute_supported() -> bool");
   m.impl("moe_permute_unpermute_supported", &moe_permute_unpermute_supported);

csrc/ops.h

@@ -292,6 +292,11 @@ void per_token_group_quant_fp8(const torch::Tensor& input,
                                torch::Tensor& output_q, torch::Tensor& output_s,
                                int64_t group_size, double eps, double fp8_min,
                                double fp8_max, bool scale_ue8m0);
+
+void per_token_group_quant_int8(const torch::Tensor& input,
+                                torch::Tensor& output_q,
+                                torch::Tensor& output_s, int64_t group_size,
+                                double eps, double int8_min, double int8_max);
 #endif
 
 void static_scaled_int8_quant(torch::Tensor& out, torch::Tensor const& input,

csrc/quantization/activation_kernels.cu

@@ -4,7 +4,7 @@
 
 #include <cmath>
 #include "core/math.hpp"
-#include "cuda_compat.h"
+#include "../cuda_compat.h"
 #include "dispatch_utils.h"
 
 #include "quantization/fp8/common.cuh"

csrc/quantization/compressed_tensors/int8_quant_kernels.cu

@@ -1,6 +1,10 @@
 #include <ATen/cuda/CUDAContext.h>
 #include <torch/all.h>
 
+#ifndef USE_ROCM
+  #include "../per_token_group_quant_8bit.h"
+#endif
+
 #include <cmath>
 
 #include "../../dispatch_utils.h"
@@ -336,3 +340,13 @@ void dynamic_scaled_int8_quant(
         }
       });
 }
+
+#ifndef USE_ROCM
+void per_token_group_quant_int8(const torch::Tensor& input,
+                                torch::Tensor& output_q,
+                                torch::Tensor& output_s, int64_t group_size,
+                                double eps, double int8_min, double int8_max) {
+  per_token_group_quant_8bit(input, output_q, output_s, group_size, eps,
+                             int8_min, int8_max);
+}
+#endif

csrc/quantization/cutlass_w8a8/Epilogues.md

@@ -86,6 +86,7 @@ D = s_a s_b \widehat A \widehat B
 ```
 
 Epilogue parameters:
+
 - `scale_a` is the scale for activations, can be per-tensor (scalar) or per-token (column-vector).
 - `scale_b` is the scale for weights, can be per-tensor (scalar) or per-channel (row-vector).
 
@@ -135,7 +136,7 @@ That is precomputed and stored in `azp_with_adj` as a row-vector.
 Epilogue parameters:
 
 - `scale_a` is the scale for activations, can be per-tensor (scalar) or per-token (column-vector).
-  - Generally this will be per-tensor as the zero-points are per-tensor.
+    - Generally this will be per-tensor as the zero-points are per-tensor.
 - `scale_b` is the scale for weights, can be per-tensor (scalar) or per-channel (row-vector).
 - `azp_with_adj` is the precomputed zero-point term ($` z_a J_a \widehat B `$), is per-channel (row-vector).
 - `bias` is the bias, is always per-channel (row-vector).
@@ -152,7 +153,7 @@ That means the zero-point term $` z_a J_a \widehat B `$ becomes an outer product
 Epilogue parameters:
 
 - `scale_a` is the scale for activations, can be per-tensor (scalar) or per-token (column-vector).
-  - Generally this will be per-token as the zero-points are per-token.
+    - Generally this will be per-token as the zero-points are per-token.
 - `scale_b` is the scale for weights, can be per-tensor (scalar) or per-channel (row-vector).
 - `azp_adj` is the precomputed zero-point adjustment term ($` \mathbf 1 \widehat B `$), is per-channel (row-vector).
 - `azp` is the zero-point (`z_a`), is per-token (column-vector).

csrc/quantization/cutlass_w8a8/c3x/scaled_mm_blockwise_sm120_fp8.cu

@@ -0,0 +1,23 @@
+#include "scaled_mm_kernels.hpp"
+#include "scaled_mm_blockwise_sm120_fp8_dispatch.cuh"
+#include "cutlass_extensions/epilogue/scaled_mm_epilogues_c3x.hpp"
+
+namespace vllm {
+
+void cutlass_scaled_mm_blockwise_sm120_fp8(torch::Tensor& out,
+                                           torch::Tensor const& a,
+                                           torch::Tensor const& b,
+                                           torch::Tensor const& a_scales,
+                                           torch::Tensor const& b_scales) {
+  if (out.dtype() == torch::kBFloat16) {
+    cutlass_gemm_blockwise_sm120_fp8_dispatch<cutlass::bfloat16_t>(
+        out, a, b, a_scales, b_scales);
+
+  } else {
+    TORCH_CHECK(out.dtype() == torch::kFloat16);
+    cutlass_gemm_blockwise_sm120_fp8_dispatch<cutlass::half_t>(
+        out, a, b, a_scales, b_scales);
+  }
+}
+
+}  // namespace vllm

csrc/quantization/cutlass_w8a8/c3x/scaled_mm_blockwise_sm120_fp8_dispatch.cuh

@@ -0,0 +1,183 @@
+#pragma once
+
+#include "cuda_utils.h"
+#include "cutlass/cutlass.h"
+#include "cutlass/numeric_types.h"
+
+#include "cute/tensor.hpp"
+#include "cutlass/tensor_ref.h"
+#include "cutlass/gemm/dispatch_policy.hpp"
+#include "cutlass/gemm/collective/collective_builder.hpp"
+#include "cutlass/gemm/device/gemm_universal_adapter.h"
+#include "cutlass/gemm/kernel/gemm_universal.hpp"
+#include "cutlass/gemm/kernel/tile_scheduler_params.h"
+#include "cutlass/epilogue/dispatch_policy.hpp"
+#include "cutlass/epilogue/collective/collective_builder.hpp"
+
+#include "cutlass_extensions/gemm/dispatch_policy.hpp"
+#include "cutlass_extensions/gemm/collective/collective_builder.hpp"
+
+#include "cutlass_gemm_caller.cuh"
+
+namespace vllm {
+
+using namespace cute;
+
+// clang-format off
+template <class OutType, int ScaleGranularityM,
+          int ScaleGranularityN, int ScaleGranularityK,
+          class MmaTileShape, class ClusterShape,
+          class EpilogueScheduler, class MainloopScheduler>
+struct cutlass_3x_gemm_fp8_blockwise {
+  using ElementAB = cutlass::float_e4m3_t;
+
+  using ElementA = ElementAB;
+  using LayoutA = cutlass::layout::RowMajor;
+  using LayoutA_Transpose = typename cutlass::layout::LayoutTranspose<LayoutA>::type;
+  static constexpr int AlignmentA = 128 / cutlass::sizeof_bits<ElementA>::value;
+
+  using ElementB = ElementAB;
+  // ColumnMajor is used for B to match the CUTLASS convention.
+  using LayoutB = cutlass::layout::ColumnMajor;
+  using LayoutB_Transpose = typename cutlass::layout::LayoutTranspose<LayoutB>::type;
+  static constexpr int AlignmentB = 128 / cutlass::sizeof_bits<ElementB>::value;
+
+  using ElementD = OutType;
+  using LayoutD = cutlass::layout::RowMajor;
+  using LayoutD_Transpose = typename cutlass::layout::LayoutTranspose<LayoutD>::type;
+  static constexpr int AlignmentD = 128 / cutlass::sizeof_bits<ElementD>::value;
+
+  using ElementC = void; // TODO: support bias
+  using LayoutC = LayoutD;
+  using LayoutC_Transpose = LayoutD_Transpose;
+  static constexpr int AlignmentC = AlignmentD;
+
+  using ElementAccumulator = float;
+  using ElementCompute = float;
+  using ElementBlockScale = float; 
+
+  using ScaleConfig = cutlass::detail::Sm120BlockwiseScaleConfig<
+        ScaleGranularityM, ScaleGranularityN, ScaleGranularityK,
+        cute::UMMA::Major::MN, cute::UMMA::Major::K>;
+
+  // layout_SFA and layout_SFB cannot be swapped since they are deduced.
+  using LayoutSFA = decltype(ScaleConfig::deduce_layoutSFA());
+  using LayoutSFB = decltype(ScaleConfig::deduce_layoutSFB());
+
+  using ArchTag = cutlass::arch::Sm120;
+  using OperatorClass = cutlass::arch::OpClassTensorOp;
+
+  static constexpr auto RoundStyle = cutlass::FloatRoundStyle::round_to_nearest;
+  using ElementScalar = float;
+  using DefaultOperation = cutlass::epilogue::fusion::LinearCombination<ElementD, ElementCompute, ElementC, ElementScalar, RoundStyle>;
+  using CollectiveEpilogue = typename cutlass::epilogue::collective::CollectiveBuilder<
+      ArchTag,
+      OperatorClass,
+      MmaTileShape,
+      ClusterShape,
+      cutlass::epilogue::collective::EpilogueTileAuto,
+      ElementAccumulator,
+      ElementCompute,
+      ElementC,
+      LayoutC,
+      AlignmentC,
+      ElementD,
+      LayoutD,
+      AlignmentD,
+      EpilogueScheduler,
+      DefaultOperation
+  >::CollectiveOp;
+ 
+  using StageCountType = cutlass::gemm::collective::StageCountAuto; 
+  using CollectiveMainloop = 
+      typename cutlass::gemm::collective::CollectiveBuilder<
+          ArchTag,
+          OperatorClass,
+          ElementA,
+          cute::tuple<LayoutA, LayoutSFA>,
+          AlignmentA,
+          ElementB,
+          cute::tuple<LayoutB, LayoutSFB>,
+          AlignmentB,
+          ElementAccumulator,
+          MmaTileShape,
+          ClusterShape,
+          cutlass::gemm::collective::StageCountAutoCarveout<static_cast<int>(sizeof(typename CollectiveEpilogue::SharedStorage))>,
+          MainloopScheduler
+      >::CollectiveOp;
+
+  using KernelType = enable_sm120_only<cutlass::gemm::kernel::GemmUniversal<
+      Shape<int, int, int, int>, CollectiveMainloop, CollectiveEpilogue>>;
+
+  struct GemmKernel : public KernelType {};
+};
+
+template <typename Gemm>
+void cutlass_gemm_caller_blockwise(torch::Tensor& out, torch::Tensor const& a,
+                                   torch::Tensor const& b,
+                                   torch::Tensor const& a_scales,
+                                   torch::Tensor const& b_scales) {
+  using GemmKernel = typename Gemm::GemmKernel;
+  using StrideA = typename Gemm::GemmKernel::StrideA;
+  using StrideB = typename Gemm::GemmKernel::StrideB;
+  using StrideD = typename Gemm::GemmKernel::StrideD;
+  using StrideC = typename Gemm::GemmKernel::StrideC;
+  using LayoutSFA = typename Gemm::LayoutSFA;
+  using LayoutSFB = typename Gemm::LayoutSFB;
+  using ScaleConfig = typename Gemm::ScaleConfig;
+
+  using ElementAB = typename Gemm::ElementAB;
+  using ElementD = typename Gemm::ElementD;
+
+  int32_t m = a.size(0), n = b.size(1), k = a.size(1);
+
+  StrideA a_stride;
+  StrideB b_stride;
+  StrideC c_stride;
+  a_stride =
+      cutlass::make_cute_packed_stride(StrideA{}, cute::make_shape(m, k, 1));
+  b_stride =
+      cutlass::make_cute_packed_stride(StrideB{}, cute::make_shape(n, k, 1));
+  c_stride =
+      cutlass::make_cute_packed_stride(StrideC{}, cute::make_shape(m, n, 1));
+
+  LayoutSFA layout_SFA = 
+      ScaleConfig::tile_atom_to_shape_SFA(make_shape(m, n, k, 1));
+  LayoutSFB layout_SFB = 
+      ScaleConfig::tile_atom_to_shape_SFB(make_shape(m, n, k, 1));
+
+  auto a_ptr = static_cast<ElementAB*>(a.data_ptr());
+  auto b_ptr = static_cast<ElementAB*>(b.data_ptr());
+  auto a_scales_ptr = static_cast<float*>(a_scales.data_ptr());
+  auto b_scales_ptr = static_cast<float*>(b_scales.data_ptr());
+
+  auto mainloop_args = [&](){
+    return typename GemmKernel::MainloopArguments{
+        a_ptr,        a_stride,   b_ptr,        b_stride,
+        a_scales_ptr, layout_SFA, b_scales_ptr, layout_SFB
+    };
+  }();
+  auto prob_shape = cute::make_shape(m, n, k, 1);
+
+  auto c_ptr = static_cast<ElementD*>(out.data_ptr());
+  typename GemmKernel::EpilogueArguments epilogue_args{
+      {}, c_ptr, c_stride, c_ptr, c_stride};
+  c3x::cutlass_gemm_caller<GemmKernel>(a.device(), prob_shape, mainloop_args,
+                                       epilogue_args);
+}
+
+template <typename OutType>
+void cutlass_gemm_blockwise_sm120_fp8_dispatch(torch::Tensor& out,
+                                               torch::Tensor const& a,
+                                               torch::Tensor const& b,
+                                               torch::Tensor const& a_scales,
+                                               torch::Tensor const& b_scales) {
+  // TODO: better heuristics
+  cutlass_gemm_caller_blockwise<cutlass_3x_gemm_fp8_blockwise<
+      OutType, 1, 128, 128, Shape<_128, _128, _128>,
+      Shape<_1, _1, _1>, cutlass::epilogue::collective::EpilogueScheduleAuto,
+      cutlass::gemm::collective::KernelScheduleAuto>>(
+      out, a, b, a_scales, b_scales);
+}
+
+}  // namespace vllm

csrc/quantization/cutlass_w8a8/c3x/scaled_mm_kernels.hpp

@@ -47,4 +47,10 @@ void cutlass_scaled_mm_blockwise_sm100_fp8(torch::Tensor& out,
                                            torch::Tensor const& b,
                                            torch::Tensor const& a_scales,
                                            torch::Tensor const& b_scales);
+
+void cutlass_scaled_mm_blockwise_sm120_fp8(torch::Tensor& out,
+                                           torch::Tensor const& a,
+                                           torch::Tensor const& b,
+                                           torch::Tensor const& a_scales,
+                                           torch::Tensor const& b_scales);
 }  // namespace vllm

csrc/quantization/cutlass_w8a8/c3x/scaled_mm_sm90_fp8.cu

@@ -1,6 +1,5 @@
 #include "scaled_mm_kernels.hpp"
 #include "scaled_mm_sm90_fp8_dispatch.cuh"
-#include "cutlass_extensions/epilogue/scaled_mm_epilogues_c3x.hpp"
 
 namespace vllm {
 
@@ -13,11 +12,11 @@ void cutlass_scaled_mm_sm90_fp8(torch::Tensor& out, torch::Tensor const& a,
   if (bias) {
     TORCH_CHECK(bias->dtype() == out.dtype(),
                 "currently bias dtype must match output dtype ", out.dtype());
-    return cutlass_scaled_mm_sm90_fp8_epilogue<c3x::ScaledEpilogueBias>(
-        out, a, b, a_scales, b_scales, *bias);
+    return cutlass_scaled_mm_sm90_fp8_epilogue<true>(out, a, b, a_scales,
+                                                     b_scales, *bias);
   } else {
-    return cutlass_scaled_mm_sm90_fp8_epilogue<c3x::ScaledEpilogue>(
-        out, a, b, a_scales, b_scales);
+    return cutlass_scaled_mm_sm90_fp8_epilogue<false>(out, a, b, a_scales,
+                                                      b_scales);
   }
 }