Skip to content

GitLab

Unverified Commit 276738ce authored by Isotr0py's avatar Isotr0py Committed by GitHub
Browse files

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


Signed-off-by: default avatarIsotr0py <2037008807@qq.com>
parent cdf22afd
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 4 deletions
vllm/model_executor/layers/quantization/utils/w8a8_utils.py
View file @ 276738ce
...@@ -11,8 +11,7 @@ TORCH_DEVICE_IDENTITY = torch.ones(1, dtype=torch.float32) ...@@ -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: ...@@ -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()
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment