[XPU][CI]Add parallelism for long-running Intel GPU cases (#52257)

Signed-off-by: zengxian <xiangdong.zeng@intel.com>

.buildkite/hardware_tests/intel_xpu_ci/test-intel.yaml

@@ -57,6 +57,7 @@ steps:
       - >-
         bash .buildkite/scripts/hardware_ci/run-intel-test.sh
         'bash .buildkite/scripts/hardware_ci/run-intel-ci-test.sh v1'
+    parallelism: 2
   - label: "XPU server test"
     depends_on:
       - image-build-xpu

.buildkite/intel_jobs/misc_intel.yaml

@@ -71,10 +71,9 @@ steps:
       export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
       cd tests &&
       pytest -v -s v1/logits_processors --ignore=v1/logits_processors/test_custom_online.py --ignore=v1/logits_processors/test_custom_offline.py &&
-      pytest -v -s v1/test_oracle.py &&
-      pytest -v -s v1/test_request.py &&
-      pytest -v -s v1/test_outputs.py &&
+      pytest -v -s v1/test_oracle.py v1/test_request.py v1/test_outputs.py &&
       pytest -v -s v1/sample'
+  parallelism: 4
 
 - label: Basic Models Tests (Initialization)
   timeout_in_minutes: 60

.buildkite/intel_jobs/test-intel.yaml

@@ -105,6 +105,7 @@ steps:
         pytest -v -s v1/e2e/general/test_correctness_sliding_window.py &&
         pytest -v -s v1/spec_decode --ignore=v1/spec_decode/test_max_len.py --ignore=v1/spec_decode/test_speculators_eagle3.py --ignore=v1/spec_decode/test_acceptance_length.py --ignore=v1/spec_decode/test_speculators_correctness.py &&
         pytest -v -s v1/kv_connector/unit --ignore=v1/kv_connector/unit/test_lmcache_integration.py --ignore=v1/kv_connector/unit/test_hf3fs_client.py --ignore=v1/kv_connector/unit/test_hf3fs_connector.py --ignore=v1/kv_connector/unit/test_hf3fs_metadata_server.py --ignore=v1/kv_connector/unit/test_offloading_connector.py'
+    parallelism: 2
   - label: "XPU server test"
     depends_on:
       - image-build-xpu

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

@@ -22,6 +22,11 @@ fi
 export PYTHONPATH=".."
 export VLLM_DISABLE_COMPILE_CACHE=1
 
+if [[ "${BUILDKITE_PARALLEL_JOB_COUNT:-1}" -gt 1 ]]; then
+  PYTEST_ADDOPTS="${PYTEST_ADDOPTS:+${PYTEST_ADDOPTS} }--num-shards=${BUILDKITE_PARALLEL_JOB_COUNT} --shard-id=${BUILDKITE_PARALLEL_JOB:-0}"
+  export PYTEST_ADDOPTS
+fi
+
 ###############################################################################
 # Helper Functions
 ###############################################################################
@@ -369,6 +374,7 @@ export HF_TOKEN ZE_AFFINITY_MASK VLLM_DISABLE_COMPILE_CACHE
     -e VLLM_DISABLE_COMPILE_CACHE \
     -e BUILDKITE_PARALLEL_JOB \
     -e BUILDKITE_PARALLEL_JOB_COUNT \
+    -e PYTEST_ADDOPTS \
     -e CMDS \
     --name "${container_name}" \
     "${IMAGE}" \