Skip to content
This repository has been archived by the owner on Oct 11, 2024. It is now read-only.

Enable bfloat16 for sparse_w16a16 #18

Merged
merged 1 commit into from
Feb 16, 2024
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion vllm/model_executor/layers/sparsity/sparse_w16a16.py
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,7 @@ def get_name(cls) -> str:

@classmethod
def get_supported_act_dtypes(cls) -> List[torch.dtype]:
return [torch.half]
return [torch.float16, torch.bfloat16]

@classmethod
def get_min_capability(cls) -> int:
Expand Down
Loading