[CPU] Enable data parallel for CPU backend (#23903)

Signed-off-by: jiang1.li <jiang1.li@intel.com>
This commit is contained in:
Li, Jiang
2025-08-29 17:19:58 +08:00
committed by GitHub
parent 2554b27baa
commit ad39106b16
6 changed files with 48 additions and 9 deletions

View File

@ -43,7 +43,7 @@ docker build -f docker/Dockerfile.cpu \
# Launching OpenAI server
docker run --rm \
--privileged=true \
--security-opt seccomp=unconfined \
--shm-size=4g \
-p 8000:8000 \
-e VLLM_CPU_KVCACHE_SPACE=<KV cache space> \