[CI][XPU] Add VLLM_DISABLE_COMPILE_CACHE=1 for other random failed cases in Intel GPU CI (#51604)

Signed-off-by: zengxian <xiangdong.zeng@intel.com>
This commit is contained in:
xiangdong
2026-08-10 17:32:16 +08:00
committed by GitHub
parent 243c63baf5
commit 51562de5ab
3 changed files with 6 additions and 4 deletions
+2 -1
View File
@@ -19,8 +19,9 @@ steps:
source_file_dependencies:
- vllm/
- tests/benchmarks/
# Remove VLLM_DISABLE_COMPILE_CACHE=1 once intel/intel-xpu-backend-for-triton#7682 is fixed
commands:
- >-
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
'cd tests &&
pytest -v -s benchmarks/'
VLLM_DISABLE_COMPILE_CACHE=1 pytest -v -s benchmarks/'
+2 -1
View File
@@ -91,6 +91,7 @@ steps:
source_file_dependencies:
- vllm/
- .buildkite/intel_jobs/test-intel.yaml
# Remove VLLM_DISABLE_COMPILE_CACHE=1 once intel/intel-xpu-backend-for-triton#7682 is fixed
commands:
- >-
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
@@ -101,7 +102,7 @@ steps:
pytest -v -s v1/worker --ignore=v1/worker/test_gpu_model_runner.py --ignore=v1/worker/test_worker_memory_snapshot.py &&
pytest -v -s v1/structured_output &&
pytest -v -s v1/test_serial_utils.py &&
pytest -v -s v1/e2e/general/test_correctness_sliding_window.py &&
VLLM_DISABLE_COMPILE_CACHE=1 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_multi_connector.py --ignore=v1/kv_connector/unit/test_example_connector.py --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'
- label: "XPU server test"
@@ -28,14 +28,14 @@ case "${test_suite}" in
;;
v1)
cd tests
# Remove VLLM_DISABLE_COMPILE_CACHE=1 once intel/intel-xpu-backend-for-triton#7682 is fixed
pytest -v -s v1/core --ignore=v1/core/test_reset_prefix_cache_e2e.py --ignore=v1/core/test_scheduler_e2e.py
pytest -v -s v1/engine --ignore=v1/engine/test_output_processor.py
pytest -v -s v1/sample --ignore=v1/sample/test_logprobs.py --ignore=v1/sample/test_logprobs_e2e.py -k "not test_topk_only and not test_topp_only and not test_topk_and_topp"
pytest -v -s v1/worker --ignore=v1/worker/test_gpu_model_runner.py --ignore=v1/worker/test_worker_memory_snapshot.py
pytest -v -s v1/structured_output
pytest -v -s v1/test_serial_utils.py
pytest -v -s v1/e2e/general/test_correctness_sliding_window.py
VLLM_DISABLE_COMPILE_CACHE=1 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_multi_connector.py --ignore=v1/kv_connector/unit/test_example_connector.py --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
;;