frozenleaves/vllm
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2025-10-20 14:53:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI Failure] Skip failing nvfp4 silu test (#23959)

Browse Source 
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
This commit is contained in:
Michael Goin
2025-09-02 13:18:15 -04:00
committed by GitHub
parent e0653f6c0b
commit e66ed3e675
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tests/kernels/quantization/test_silu_nvfp4_quant_fusion.py
View File

@ -8,7 +8,8 @@ from vllm.model_executor.layers.activation import SiluAndMul
from vllm.platforms import current_platform
from vllm.scalar_type import scalar_types
if not current_platform.has_device_capability(100):
if not (current_platform.has_device_capability(100)
and hasattr(torch.ops._C, "silu_and_mul_nvfp4_quant")):
pytest.skip(reason="Nvfp4 Requires compute capability of 10 or above.",
allow_module_level=True)