biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Bugfix][CPU] Skip set_num_threads after thread binding (#38535)

Browse Source 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
This commit is contained in:
Li, Jiang
2026-03-30 20:13:00 +08:00
committed by GitHub
parent 677424c7ac
commit 6557f4937f
2 changed files with 12 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
.buildkite/scripts/hardware_ci/run-cpu-distributed-smoke-test.sh
View File

@@ -1,9 +1,10 @@
#!/bin/bash
set -euox pipefail
export VLLM_CPU_CI_ENV=0
export VLLM_CPU_KVCACHE_SPACE=1 # avoid OOM
echo "--- PP+TP"
vllm serve meta-llama/Llama-3.2-3B-Instruct -tp=2 -pp=2 &
vllm serve meta-llama/Llama-3.2-3B-Instruct -tp=2 -pp=2 --max-model-len=4096 &
server_pid=$!
timeout 600 bash -c "until curl localhost:8000/v1/models > /dev/null 2>&1; do sleep 1; done" || exit 1
vllm bench serve \
@@ -23,7 +24,7 @@ if [ "$failed_req" -ne 0 ]; then
fi
echo "--- DP+TP"
vllm serve meta-llama/Llama-3.2-3B-Instruct -tp=2 -dp=2 &
vllm serve meta-llama/Llama-3.2-3B-Instruct -tp=2 -dp=2 --max-model-len=4096 &
server_pid=$!
timeout 600 bash -c "until curl localhost:8000/v1/models > /dev/null 2>&1; do sleep 1; done" || exit 1
vllm bench serve \