From 2967e5e22ab2e12888464c01100b2ddeed34720a Mon Sep 17 00:00:00 2001 From: Li Wang Date: Sun, 7 Sep 2025 10:36:34 +0800 Subject: [PATCH] [Benchmark] Correctly kill vllm process in performance benchamrk (#2782) ### What this PR does / why we need it? vLLM now names the process with VLLM prefix after https://github.com/vllm-project/vllm/pull/21445, we should kill the correct process name after one iteration benchmark to avoid OOM issue ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? - vLLM version: v0.10.1.1 - vLLM main: https://github.com/vllm-project/vllm/commit/e599e2c65ee32abcc986733ab0a55becea158bb4 --------- Signed-off-by: wangli --- benchmarks/scripts/run-performance-benchmarks.sh | 4 +++- benchmarks/tests/serving-tests.json | 3 ++- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/benchmarks/scripts/run-performance-benchmarks.sh b/benchmarks/scripts/run-performance-benchmarks.sh index b604fe9..befdf69 100644 --- a/benchmarks/scripts/run-performance-benchmarks.sh +++ b/benchmarks/scripts/run-performance-benchmarks.sh @@ -78,7 +78,9 @@ kill_npu_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 + sleep 4 rm -rf ~/.config/vllm diff --git a/benchmarks/tests/serving-tests.json b/benchmarks/tests/serving-tests.json index 6398710..c2be9eb 100644 --- a/benchmarks/tests/serving-tests.json +++ b/benchmarks/tests/serving-tests.json @@ -23,7 +23,8 @@ "hf_split": "train", "endpoint": "/v1/chat/completions", "dataset_path": "lmarena-ai/vision-arena-bench-v0.1", - "num_prompts": 200 + "num_prompts": 200, + "no_stream": "" } }, {