Skip to content

GitLab

Commit 9d16d5aa authored by zhuwenwen's avatar zhuwenwen
Browse files

update unified_attention_with_output_fake

parent 9dd70f0e
Show whitespace changes
Inline Side-by-side
Showing with 2 additions and 0 deletions
vllm/attention/layer.py
View file @ 9d16d5aa
...@@ -566,6 +566,8 @@ def unified_attention_with_output_fake( ...@@ -566,6 +566,8 @@ def unified_attention_with_output_fake(
output: torch.Tensor, output: torch.Tensor,
layer_name: str, layer_name: str,
output_scale: Optional[torch.Tensor] = None, output_scale: Optional[torch.Tensor] = None,
query_nope: Optional[torch.Tensor] = None,
num_local_heads: Optional[int] = None,
q_ori: Optional[torch.Tensor] = None, q_ori: Optional[torch.Tensor] = None,
key_normed: Optional[torch.Tensor] = None, key_normed: Optional[torch.Tensor] = None,
positions: Optional[torch.Tensor] = None, positions: Optional[torch.Tensor] = None,
......
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