xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-24 00:45:02 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI/Build][AMD] Skip test_cutlass_w4a8_moe tests on ROCm sine they require cutlass_pack_scale_fp8 (#30508)

Browse Source 
Signed-off-by: Randall Smith <ransmith@amd.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
rasmith 2025-12-11 19:02:19 -06:00 committed by GitHub
parent 0ab23c2b2b
commit ba80926681
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
tests/kernels/quantization/test_cutlass_w4a8_moe.py
View File

@ -18,7 +18,9 @@ from vllm.model_executor.layers.quantization.utils.quant_utils import (
from vllm.platforms import current_platform from vllm.platforms import current_platform
from vllm.scalar_type import ScalarType, scalar_types from vllm.scalar_type import ScalarType, scalar_types
IS_SUPPORTED_BY_GPU = current_platform.get_device_capability()[0] >= 9 IS_SUPPORTED_BY_GPU = (
current_platform.is_cuda() and current_platform.get_device_capability()[0] >= 9
)
def to_fp8(tensor: torch.Tensor) -> torch.Tensor: def to_fp8(tensor: torch.Tensor) -> torch.Tensor: