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 14, 05:30 UTC
[CI/Build] Disable SiluMul NVFP4 quant fusion tests (#24121)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Matthew Bonanni committed
Sep 2, 2025 at 19:50 UTC
2fd1a40a54cf9a5af6f0a8ce4700faf4a1a5108b
1 file changed
+2
-2
.buildkite/test-pipeline.yaml
+2
-2
@@ -666,7 +666,7 @@ steps:
666
# Quantization
667
- pytest -v -s tests/kernels/quantization/test_cutlass_scaled_mm.py -k 'fp8'
668
- pytest -v -s tests/kernels/quantization/test_nvfp4_quant.py
669
- - pytest -v -s tests/kernels/quantization/test_silu_nvfp4_quant_fusion.py
669
+ # - pytest -v -s tests/kernels/quantization/test_silu_nvfp4_quant_fusion.py
670
- pytest -v -s tests/kernels/quantization/test_nvfp4_scaled_mm.py
671
- pytest -v -s tests/kernels/quantization/test_flashinfer_scaled_mm.py
672
- pytest -v -s tests/kernels/quantization/test_flashinfer_nvfp4_scaled_mm.py
@@ -676,7 +676,7 @@ steps:
676
- pytest -v -s tests/compile/test_fusion_all_reduce.py
677
- pytest -v -s tests/compile/test_fusion_attn.py::test_attention_quant_pattern
678
- pytest -v -s tests/kernels/moe/test_flashinfer.py
679
- - pytest -v -s tests/compile/test_silu_mul_quant_fusion.py
679
+ # - pytest -v -s tests/compile/test_silu_mul_quant_fusion.py
680
681
##### 1 GPU test #####
682
##### multi gpus test #####