frozenleaves/vllm
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2025-10-20 14:53:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

[XPU][CI] add v1/core test in xpu hardware ci (#20537)

Browse Source 
Signed-off-by: Ma, Liangliang <liangliang.ma@intel.com>
This commit is contained in:
Liangliang Ma
2025-07-07 16:16:40 +08:00
committed by GitHub
parent 2e610deb72
commit 2c5ebec064
3 changed files with 6 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
.buildkite/scripts/hardware_ci/run-xpu-test.sh
View File

@ -11,8 +11,8 @@ container_name="xpu_${BUILDKITE_COMMIT}_$(tr -dc A-Za-z0-9 < /dev/urandom | head
docker build -t ${image_name} -f docker/Dockerfile.xpu .
# Setup cleanup
remove_docker_container() {
docker rm -f "${container_name}" || true;
remove_docker_container() {
docker rm -f "${container_name}" || true;
docker image rm -f "${image_name}" || true;
docker system prune -f || true;
}
@ -27,4 +27,6 @@ docker run \
"${image_name}" \
sh -c '
VLLM_USE_V1=1 python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager
cd tests
pytest -v -s v1/core
'

2
docker/Dockerfile.xpu
View File

@ -47,7 +47,7 @@ FROM vllm-base AS vllm-openai
# install additional dependencies for openai api server
RUN --mount=type=cache,target=/root/.cache/pip \
pip install accelerate hf_transfer 'modelscope!=1.15.0'
pip install accelerate hf_transfer pytest 'modelscope!=1.15.0'
ENV VLLM_USAGE_SOURCE production-docker-image \
TRITON_XPU_PROFILE 1

6
vllm/platforms/xpu.py
View File

@ -93,10 +93,6 @@ class XPUPlatform(Platform):
"mode.")
model_config.enforce_eager = True
if vllm_config.speculative_config is not None:
raise NotImplementedError(
"XPU does not support speculative decoding")
if vllm_config.device_config is not None:
assert vllm_config.device_config.device_type == "xpu"
@ -181,4 +177,4 @@ class XPUPlatform(Platform):
@classmethod
def device_count(cls) -> int:
return torch.xpu.device_count()
return torch.xpu.device_count()