Skip to content

GitLab

Unverified Commit 1f18adb2 authored by Chen Zhang's avatar Chen Zhang Committed by GitHub
Browse files

[Kernel] Revert the API change of Attention.forward (#12038) 


Signed-off-by: default avatarChen Zhang <zhangch99@outlook.com>
parent bb354e6b
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
vllm/attention/layer.py
View file @ 1f18adb2
...@@ -134,8 +134,8 @@ class Attention(nn.Module): ...@@ -134,8 +134,8 @@ class Attention(nn.Module):
query: torch.Tensor, query: torch.Tensor,
key: torch.Tensor, key: torch.Tensor,
value: torch.Tensor, value: torch.Tensor,
_kv_cache: torch.Tensor, kv_cache: torch.Tensor,
_attn_metadata: AttentionMetadata, attn_metadata: AttentionMetadata,
) -> torch.Tensor: ) -> torch.Tensor:
if self.use_output: if self.use_output:
output = torch.empty_like(query) output = torch.empty_like(query)
......
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