xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-07-13 02:37:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
Gordon Wong 2025-02-22 14:07:04 +08:00 committed by GitHub
parent 68d535ef44
commit 68d630a0c7
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/attention/backends/rocm_flash_attn.py
View File

@ -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: