xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-17 05:55:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Fix broken CPU compressed-tensors test (#11338)

Browse Source 
Signed-off-by: Isotr0py <2037008807@qq.com>
This commit is contained in:
Isotr0py 2024-12-20 01:37:31 +08:00 committed by GitHub
parent cdf22afdda
commit 276738ce0f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/model_executor/layers/quantization/utils/w8a8_utils.py
View File

@ -11,8 +11,7 @@ TORCH_DEVICE_IDENTITY = torch.ones(1, dtype=torch.float32)
def sparse_cutlass_supported() -> bool: def sparse_cutlass_supported() -> bool:
# sparse cutlass is not supported on Rocm if not current_platform.is_cuda():
if current_platform.is_rocm():
return False return False
capability_tuple = current_platform.get_device_capability() capability_tuple = current_platform.get_device_capability()
@ -22,8 +21,7 @@ def sparse_cutlass_supported() -> bool:
def cutlass_fp8_supported() -> bool: def cutlass_fp8_supported() -> bool:
# cutlass is not supported on Rocm if not current_platform.is_cuda():
if current_platform.is_rocm():
return False return False
capability_tuple = current_platform.get_device_capability() capability_tuple = current_platform.get_device_capability()