From 3c8a7872471a96b414f9861653dded55aa431795 Mon Sep 17 00:00:00 2001
From: Daniel Serebrenik <74646983+pliops-daniels@users.noreply.github.com>
Date: Tue, 19 Aug 2025 10:48:07 +0300
Subject: [PATCH] [Benchmark] Add flag --served-model-name to
 benchmark_serving_multi_turn (#22889)

Signed-off-by: daniels <daniels@pliops.com>
---
 benchmarks/multi_turn/README.md                    | 12 +++++++-----
 .../multi_turn/benchmark_serving_multi_turn.py     | 14 +++++++++++++-
 2 files changed, 20 insertions(+), 6 deletions(-)

diff --git a/benchmarks/multi_turn/README.md b/benchmarks/multi_turn/README.md
index ae0866ae60..7adf97bcf5 100644
--- a/benchmarks/multi_turn/README.md
+++ b/benchmarks/multi_turn/README.md
@@ -5,11 +5,13 @@ The requirements (pip) for `benchmark_serving_multi_turn.py` can be found in `re
 First start serving your model
 
 ```bash
-export MODEL_NAME=/models/meta-llama/Meta-Llama-3.1-8B-Instruct/
+export MODEL_PATH=/models/meta-llama/Meta-Llama-3.1-8B-Instruct/
 
-vllm serve $MODEL_NAME --disable-log-requests
+vllm serve $MODEL_PATH --served-model-name Llama --disable-log-requests
 ```
 
+The variable `MODEL_PATH` should be a path to the model files (e.g. downloaded from huggingface).
+
 ## Synthetic Multi-Turn Conversations
 
 Download the following text file (used for generation of synthetic conversations)
@@ -26,10 +28,10 @@ But you may use other text files if you prefer (using this specific file is not
 Then run the benchmarking script
 
 ```bash
-export MODEL_NAME=/models/meta-llama/Meta-Llama-3.1-8B-Instruct/
+export MODEL_PATH=/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
+python benchmark_serving_multi_turn.py --model $MODEL_PATH --served-model-name Llama \
+--input-file generate_multi_turn.json --num-clients 2 --max-active-conversations 6
 ```
 
 You can edit the file `generate_multi_turn.json` to change the conversation parameters (number of turns, etc.).
diff --git a/benchmarks/multi_turn/benchmark_serving_multi_turn.py b/benchmarks/multi_turn/benchmark_serving_multi_turn.py
index 53c3207491..d23b7b6e45 100644
--- a/benchmarks/multi_turn/benchmark_serving_multi_turn.py
+++ b/benchmarks/multi_turn/benchmark_serving_multi_turn.py
@@ -825,9 +825,11 @@ def get_client_config(
 
     # Arguments for API requests
     chat_url = f"{args.url}/v1/chat/completions"
+    model_name = args.served_model_name if args.served_model_name else args.model
+
     req_args = RequestArgs(
         chat_url=chat_url,
-        model=args.model,
+        model=model_name,
         stream=not args.no_stream,
         limit_min_tokens=args.limit_min_tokens,
         limit_max_tokens=args.limit_max_tokens,
@@ -1247,9 +1249,19 @@ async def main() -> None:
         default=0,
         help="Seed for random number generators (default: 0)",
     )
+
     parser.add_argument(
         "-m", "--model", type=str, required=True, help="Path of the LLM model"
     )
+    parser.add_argument(
+        "--served-model-name",
+        type=str,
+        default=None,
+        help="The model name used in the API. "
+        "If not specified, the model name will be the "
+        "same as the ``--model`` argument. ",
+    )
+
     parser.add_argument(
         "-u",
         "--url",