[ZenCPU] Changes with respect to relevant cpu tests for ZenDNN

Signed-off-by: Chinmay Kulkarni <Chinmay.Kulkarni@amd.com>

.buildkite/hardware_tests/zen.yaml

@@ -0,0 +1,25 @@
+group: Zen CPU
+depends_on: []
+steps:
+- label: Zen-CPU-Kernel Tests
+  depends_on: []
+  soft_fail: false
+  device: zen5
+  no_plugin: true
+  source_file_dependencies:
+  - setup.py
+  - docker/Dockerfile.cpu
+  - requirements/cpu.txt
+  - requirements/build/cpu.txt
+  - csrc/cpu/
+  - cmake/cpu_extension.cmake
+  - CMakeLists.txt
+  - vllm/model_executor/layers/utils.py
+  - vllm/platforms/cpu.py
+  - vllm/platforms/zen_cpu.py
+  - vllm/platforms/__init__.py
+  - tests/model_executor/test_cpu_unquantized_gemm_dispatch.py
+  commands:
+    - |
+      bash .buildkite/scripts/hardware_ci/run-zen-cpu-test.sh 20m "
+      pytest -x -v -s tests/model_executor/test_cpu_unquantized_gemm_dispatch.py"

.buildkite/scripts/hardware_ci/run-zen-cpu-test.sh

@@ -0,0 +1,20 @@
+#!/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 -euox pipefail
+
+# allow to bind to different cores
+CORE_RANGE=${CORE_RANGE:-48-95}
+NUMA_NODE=${NUMA_NODE:-1}
+IMAGE_NAME="zen-cpu-test-$NUMA_NODE"
+TIMEOUT_VAL=$1
+TEST_COMMAND=$2
+
+# building the docker image
+echo "--- :docker: Building Docker image"
+docker build --progress plain --tag "$IMAGE_NAME" --target vllm-zen-test -f docker/Dockerfile.cpu .
+
+# Run the image, setting --shm-size=4g for tensor parallel.
+docker run --rm --cpuset-cpus="$CORE_RANGE" --cpuset-mems="$NUMA_NODE" -v ~/.cache/huggingface:/root/.cache/huggingface --privileged=true -e HF_TOKEN -e VLLM_CPU_KVCACHE_SPACE=16 -e VLLM_CPU_CI_ENV=1 -e VLLM_CPU_SIM_MULTI_NUMA=1 --shm-size=4g "$IMAGE_NAME" \
+        timeout "$TIMEOUT_VAL" bash -c "set -euox pipefail; echo \"--- Print packages\"; pip list; echo \"--- Running tests\"; ${TEST_COMMAND}"

docker/Dockerfile.cpu

@@ -318,3 +318,30 @@ RUN --mount=type=cache,target=/root/.cache/uv \
     uv pip install "vllm[zen]"
 
 ENTRYPOINT ["vllm", "serve"]
+
+######################### ZEN CPU TEST IMAGE #########################
+FROM vllm-openai-zen AS vllm-zen-test
+
+WORKDIR /vllm-workspace
+
+COPY --from=vllm-test-deps /vllm-workspace/requirements/test/cpu.txt requirements/test/cpu.txt
+
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv pip install -r requirements/test/cpu.txt
+
+ADD ./tests/ ./tests/
+ADD ./examples/ ./examples/
+ADD ./benchmarks/ ./benchmarks/
+ADD ./vllm/collect_env.py .
+ADD ./docker/ ./docker/
+ADD ./.buildkite/ ./.buildkite/
+
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv pip install -e tests/vllm_test_utils
+
+# enable fast downloads from hf (for testing)
+ENV HF_XET_HIGH_PERFORMANCE=1
+# increase timeout for hf downloads (for testing)
+ENV HF_HUB_DOWNLOAD_TIMEOUT=60
+
+ENTRYPOINT []