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

Signed-off-by: Chendi.Xue <chendi.xue@intel.com>

.buildkite/run-hpu-test.sh

+#!/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
\ No newline at end of file

Dockerfile.hpu

@@ -13,4 +13,6 @@ RUN VLLM_TARGET_DEVICE=hpu python3 setup.py install
 
 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"]