xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-10 20:36:57 +08:00
Code Issues Packages Projects Releases Wiki Activity

Correctly kill vLLM processes after finishing serving benchmarks (#21641)

Browse Source 
Signed-off-by: Huy Do <huydhn@gmail.com>
This commit is contained in:
Huy Do 2025-07-25 19:06:21 -07:00 committed by GitHub
parent 97349fe2bc
commit a55c95096b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 8 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
.buildkite/nightly-benchmarks/scripts/run-nightly-benchmarks.sh
View File

@ -95,12 +95,14 @@ json2args() {
} }
kill_gpu_processes() { kill_gpu_processes() {
pkill -f python pkill -f '[p]ython'
pkill -f python3 pkill -f '[p]ython3'
pkill -f tritonserver pkill -f '[t]ritonserver'
pkill -f pt_main_thread pkill -f '[p]t_main_thread'
pkill -f text-generation pkill -f '[t]ext-generation'
pkill -f lmdeploy 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 [ "$(nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits | head -n 1)" -ge 1000 ]; do while [ "$(nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits | head -n 1)" -ge 1000 ]; do
sleep 1 sleep 1