[XPU][UT] increase intel xpu CI test scope (#21492)

Signed-off-by: Ma, Liangliang <[email protected]>

Author: Liangliang-Ma

.buildkite/scripts/hardware_ci/run-xpu-test.sh

@@ -31,4 +31,13 @@ docker run \
     VLLM_USE_V1=1 python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend mp
     cd tests
     pytest -v -s v1/core
+    pytest -v -s v1/engine
+    pytest -v -s v1/sample --ignore=v1/sample/test_logprobs.py --ignore=v1/sample/test_logprobs_e2e.py
+    pytest -v -s v1/worker --ignore=v1/worker/test_gpu_model_runner.py
+    pytest -v -s v1/structured_output
+    pytest -v -s v1/spec_decode --ignore=v1/spec_decode/test_max_len.py --ignore=v1/spec_decode/test_eagle.py
+    pytest -v -s v1/kv_connector/unit --ignore=v1/kv_connector/unit/test_multi_connector.py --ignore=v1/kv_connector/unit/test_nixl_connector.py
+    pytest -v -s v1/test_serial_utils.py
+    pytest -v -s v1/test_utils.py
+    pytest -v -s v1/test_metrics_reader.py
 '

docker/Dockerfile.xpu

@@ -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 pytest modelscope
+    pip install accelerate hf_transfer pytest pytest_asyncio lm_eval[api] modelscope
 
 ENV VLLM_USAGE_SOURCE production-docker-image \
     TRITON_XPU_PROFILE 1

tests/entrypoints/openai/correctness/test_lmeval.py

@@ -69,8 +69,9 @@ def run_test(more_args):
 
 
 @pytest.mark.skipif(not current_platform.is_cuda()
-                    and not current_platform.is_tpu(),
-                    reason="V1 currently only supported on CUDA and TPU")
+                    and not current_platform.is_tpu()
+                    and not current_platform.is_xpu(),
+                    reason="V1 currently only supported on CUDA, XPU and TPU")
 def test_lm_eval_accuracy_v1_engine(monkeypatch: pytest.MonkeyPatch):
     """Run with the V1 Engine."""