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

[CI/Build] Add run-hpu-test.sh script (#10167)

Browse Source 
Signed-off-by: Chendi.Xue <chendi.xue@intel.com>
This commit is contained in:
Chendi.Xue 2024-11-09 00:26:52 -06:00 committed by GitHub
parent 1a95f10ee7
commit 8e1529dc57
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 18 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
.buildkite/run-hpu-test.sh Normal file
View File

@ -0,0 +1,16 @@
#!/bin/bash
# This script build the CPU docker image and run the offline inference inside the container.
# It serves a sanity check for compilation and basic model usage.
set -ex
# Try building the docker image
docker build -t hpu-test-env -f Dockerfile.hpu .
# Setup cleanup
remove_docker_container() { docker rm -f hpu-test || true; }
trap remove_docker_container EXIT
remove_docker_container
# Run the image and launch offline inference
docker run --runtime=habana --name=hpu-test --network=host -e VLLM_SKIP_WARMUP=true --entrypoint="" hpu-test-env python3 examples/offline_inference.py

2
Dockerfile.hpu
View File

@ -13,4 +13,6 @@ RUN VLLM_TARGET_DEVICE=hpu python3 setup.py install
WORKDIR /workspace/ WORKDIR /workspace/
RUN ln -s /workspace/vllm/tests && ln -s /workspace/vllm/examples && ln -s /workspace/vllm/benchmarks
ENTRYPOINT ["python3", "-m", "vllm.entrypoints.openai.api_server"] ENTRYPOINT ["python3", "-m", "vllm.entrypoints.openai.api_server"]