[CI/Build][Doc] Move existing benchmark scripts in CI/document/example to vllm bench CLI (#21355)

Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>

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

@@ -227,7 +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 $model \
@@ -248,7 +248,7 @@ run_serving_tests() {
         sonnet_output_len=$(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

@@ -206,7 +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"
 
@@ -273,7 +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"
 
@@ -394,7 +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 \

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

@@ -83,7 +83,7 @@ function cpu_tests() {
     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 \
+    vllm bench serve \
       --backend vllm \
       --dataset-name random \
       --model meta-llama/Llama-3.2-3B-Instruct \

.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/run_bm.sh

@@ -77,7 +77,7 @@ 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 \

benchmarks/README.md

@@ -98,7 +98,7 @@ 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 \
@@ -150,7 +150,7 @@ VLLM_USE_V1=1 vllm serve meta-llama/Llama-3.1-8B-Instruct --disable-log-requests
 
 ```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 \
@@ -174,7 +174,7 @@ vllm serve Qwen/Qwen2-VL-7B-Instruct --disable-log-requests
 ```
 
 ```bash
-python3 vllm/benchmarks/benchmark_serving.py \
+vllm bench serve \
   --backend openai-chat \
   --model Qwen/Qwen2-VL-7B-Instruct \
   --endpoint /v1/chat/completions \
@@ -194,7 +194,7 @@ 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 \
@@ -210,7 +210,7 @@ vllm serve Qwen/Qwen2-VL-7B-Instruct --disable-log-requests
 **`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 \
@@ -224,7 +224,7 @@ python3 vllm/benchmarks/benchmark_serving.py \
 **`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 \
@@ -237,7 +237,7 @@ python3 vllm/benchmarks/benchmark_serving.py \
 **`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 \
@@ -248,7 +248,7 @@ python3 vllm/benchmarks/benchmark_serving.py \
 **`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 \
@@ -261,7 +261,7 @@ 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 \
@@ -296,7 +296,7 @@ The following arguments can be used to control the ramp-up:
 <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 \
@@ -314,7 +314,7 @@ Total num output tokens:  1500
 **VisionArena Benchmark for Vision Language Models**
 
 ``` bash
-python3 vllm/benchmarks/benchmark_throughput.py \
+vllm bench throughput \
   --model Qwen/Qwen2-VL-7B-Instruct \
   --backend vllm-chat \
   --dataset-name hf \
@@ -336,7 +336,7 @@ Total num output tokens:  1280
 ``` 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 \
@@ -360,7 +360,7 @@ Total num output tokens:  204800
 **`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 \
@@ -373,7 +373,7 @@ python3 vllm/benchmarks/benchmark_throughput.py \
 **`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 \
@@ -385,7 +385,7 @@ python3 vllm/benchmarks/benchmark_throughput.py \
 **`AI-MO/aimo-validation-aime`**
 
 ```bash
-python3 benchmarks/benchmark_throughput.py \
+vllm bench throughput \
   --model Qwen/QwQ-32B \
   --backend vllm \
   --dataset-name hf \
@@ -399,7 +399,7 @@ python3 benchmarks/benchmark_throughput.py \
 ``` 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 \

benchmarks/auto_tune/auto_tune.sh

@@ -136,7 +136,7 @@ run_benchmark() {
     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 \
+    vllm bench serve \
         --backend vllm \
         --model $MODEL  \
         --dataset-name random \
@@ -169,7 +169,7 @@ adjusted_input_len=$(( INPUT_LEN - prefix_len ))
             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 \

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_serving.py

@@ -38,6 +38,7 @@ 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,
@@ -593,6 +594,10 @@ 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_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,
@@ -382,6 +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

docs/contributing/profiling.md

@@ -38,7 +38,7 @@ VLLM_TORCH_PROFILER_DIR=./vllm_profile \
 benchmark_serving.py:
 
 ```bash
-python benchmarks/benchmark_serving.py \
+vllm bench serve \
     --backend vllm \
     --model meta-llama/Meta-Llama-3-70B \
     --dataset-name sharegpt \
@@ -75,7 +75,7 @@ The following is an example using the `benchmarks/benchmark_latency.py` script:
 nsys profile -o report.nsys-rep \
     --trace-fork-before-exec=true \
     --cuda-graph-trace=node \
-    python benchmarks/benchmark_latency.py \
+vllm bench latency \
     --model meta-llama/Llama-3.1-8B-Instruct \
     --num-iters-warmup 5 \
     --num-iters 1 \
@@ -98,7 +98,7 @@ nsys profile -o report.nsys-rep \
     vllm serve meta-llama/Llama-3.1-8B-Instruct
 
 # client
-python benchmarks/benchmark_serving.py \
+vllm bench serve \
     --backend vllm \
     --model meta-llama/Llama-3.1-8B-Instruct \
     --num-prompts 1 \

docs/design/v1/p2p_nccl_connector.md

@@ -291,7 +291,7 @@ curl -X POST -s http://10.0.1.1:10001/v1/completions \
 ??? console "Command"
 
     ```shell
-    python3 benchmark_serving.py \
+    vllm bench serve \
         --backend vllm \
         --model base_model \
         --tokenizer meta-llama/Llama-3.1-8B-Instruct \

examples/online_serving/disaggregated_serving_p2p_nccl_xpyd/disagg_example_p2p_nccl_xpyd.sh

@@ -233,7 +233,7 @@ main() {
     # Run Benchmark
     # =============================================================================
     cd ../../../benchmarks/
-    python3 benchmark_serving.py --port 10001 --seed $(date +%s) \
+    vllm bench serve --port 10001 --seed $(date +%s) \
         --model $MODEL \
         --dataset-name random --random-input-len 7500 --random-output-len 200 \
         --num-prompts 200 --burstiness 100 --request-rate 2 | tee benchmark.log

examples/others/lmcache/disagg_prefill_lmcache_v1/disagg_example_nixl.sh

@@ -122,7 +122,7 @@ main() {
 
     # begin benchmark
     cd ../../../../benchmarks/
-    python3 benchmark_serving.py --port 9000 --seed $(date +%s) \
+    vllm bench serve --port 9000 --seed $(date +%s) \
         --model meta-llama/Llama-3.1-8B-Instruct \
         --dataset-name random --random-input-len 7500 --random-output-len 200 \
         --num-prompts 200 --burstiness 100 --request-rate 3.6 | tee benchmark.log