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 3, 10:30 UTC
[XPU][CI] Temporarily skip test_moe_lora_align_block_size_mixed_base_and_lora[1] in Intel GPU CI (#42954)
Signed-off-by: zengxian <xiangdong.zeng@intel.com>
xiangdong committed
May 18, 2026 at 20:34 UTC
2e40faf08b2cae4ff6e27a255fe10833365de0e8
1 file changed
+1
-1
.buildkite/intel_jobs/lora_intel.yaml
+1
-1
@@ -49,7 +49,7 @@ steps:
49
'cd tests &&
50
export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
51
pytest -v -s lora/test_fused_moe_lora_kernel.py &&
52
- pytest -v -s lora/test_moe_lora_align_sum.py'
52
+ pytest -v -s lora/test_moe_lora_align_sum.py --deselect="tests/lora/test_moe_lora_align_sum.py::test_moe_lora_align_block_size_mixed_base_and_lora[1]"'
53
54
- label: LoRA Punica Kernels
55
timeout_in_minutes: 45