Skip to content

GitLab

Unverified Commit 68d630a0 authored by Gordon Wong's avatar Gordon Wong Committed by GitHub
Browse files

[ROCM] fix native attention function call (#13650)

parent 68d535ef
Hide whitespace changes
Inline Side-by-side
Showing with 0 additions and 1 deletion
vllm/attention/backends/rocm_flash_attn.py
View file @ 68d630a0
...@@ -717,7 +717,6 @@ class ROCmFlashAttentionImpl(AttentionImpl): ...@@ -717,7 +717,6 @@ class ROCmFlashAttentionImpl(AttentionImpl):
self.num_heads, self.num_heads,
self.head_size, self.head_size,
self.scale, self.scale,
causal_mask,
attn_masks, attn_masks,
) )
else: else:
......
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