A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 5, 14:45 UTC
[XPU][CI] Skip test_topk_only cases on Intel GPU in CI (#38899)
Signed-off-by: zengxian <xiangdong.zeng@intel.com>
xiangdong committed
Apr 3, 2026 at 17:50 UTC
cb4ff07f8b1747f77673222456dd3f3968aead9c
1 file changed
+1
-1
.buildkite/intel_jobs/test-intel.yaml
+1
-1
@@ -56,7 +56,7 @@ steps:
56
'cd tests &&
57
pytest -v -s v1/core --ignore=v1/core/test_reset_prefix_cache_e2e.py --ignore=v1/core/test_scheduler_e2e.py &&
58
pytest -v -s v1/engine --ignore=v1/engine/test_output_processor.py &&
59
- pytest -v -s v1/sample --ignore=v1/sample/test_logprobs.py --ignore=v1/sample/test_logprobs_e2e.py &&
59
+ pytest -v -s v1/sample --ignore=v1/sample/test_logprobs.py --ignore=v1/sample/test_logprobs_e2e.py -k "not test_topk_only" &&
60
pytest -v -s v1/worker --ignore=v1/worker/test_gpu_model_runner.py --ignore=v1/worker/test_worker_memory_snapshot.py &&
61
pytest -v -s v1/structured_output &&
62
pytest -v -s v1/test_serial_utils.py &&