diff --git a/.buildkite/run-hpu-test.sh b/.buildkite/run-hpu-test.sh
new file mode 100644
index 00000000..4505dc7a
--- /dev/null
+++ b/.buildkite/run-hpu-test.sh
@@ -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
\ No newline at end of file
diff --git a/Dockerfile.hpu b/Dockerfile.hpu
index f481c8c6..d18fc016 100644
--- a/Dockerfile.hpu
+++ b/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"]