From e98def439cc89adba6d704083c5c78dd89b51b5f Mon Sep 17 00:00:00 2001 From: Huy Do Date: Sat, 26 Jul 2025 06:06:05 -0700 Subject: [PATCH] [Take 2] Correctly kill vLLM processes after benchmarks (#21646) Signed-off-by: Huy Do --- .../nightly-benchmarks/scripts/run-performance-benchmarks.sh | 3 ++- benchmarks/disagg_benchmarks/disagg_overhead_benchmark.sh | 2 ++ benchmarks/disagg_benchmarks/disagg_performance_benchmark.sh | 2 ++ 3 files changed, 6 insertions(+), 1 deletion(-) diff --git a/.buildkite/nightly-benchmarks/scripts/run-performance-benchmarks.sh b/.buildkite/nightly-benchmarks/scripts/run-performance-benchmarks.sh index f05040618..630943c80 100644 --- a/.buildkite/nightly-benchmarks/scripts/run-performance-benchmarks.sh +++ b/.buildkite/nightly-benchmarks/scripts/run-performance-benchmarks.sh @@ -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 diff --git a/benchmarks/disagg_benchmarks/disagg_overhead_benchmark.sh b/benchmarks/disagg_benchmarks/disagg_overhead_benchmark.sh index 94999630b..b150b0194 100644 --- a/benchmarks/disagg_benchmarks/disagg_overhead_benchmark.sh +++ b/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 diff --git a/benchmarks/disagg_benchmarks/disagg_performance_benchmark.sh b/benchmarks/disagg_benchmarks/disagg_performance_benchmark.sh index eb5d891d0..c5a483f2f 100644 --- a/benchmarks/disagg_benchmarks/disagg_performance_benchmark.sh +++ b/benchmarks/disagg_benchmarks/disagg_performance_benchmark.sh @@ -18,6 +18,8 @@ kill_gpu_processes() { # kill all processes on GPU. pgrep pt_main_thread | xargs -r kill -9 pgrep python3 | xargs -r kill -9 + # vLLM now names the process with VLLM prefix after https://github.com/vllm-project/vllm/pull/21445 + pgrep VLLM | xargs -r kill -9 for port in 8000 8100 8200; do lsof -t -i:$port | xargs -r kill -9; done sleep 1 }