xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-07-19 20:27:32 +08:00
Code Issues Packages Projects Releases Wiki Activity

[attn][tiny fix] fix attn backend in MultiHeadAttention (#11463)

Browse Source 
Signed-off-by: Mengqing Cao <cmq0113@163.com>
This commit is contained in:
Mengqing Cao 2024-12-24 20:39:36 +08:00 committed by GitHub
parent 461cde2080
commit 5c7963249d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/attention/layer.py
View File

@ -191,6 +191,7 @@ class MultiHeadAttention(nn.Module):
kv_cache_dtype=None, kv_cache_dtype=None,
block_size=16, block_size=16,
is_attention_free=False) is_attention_free=False)
attn_backend = backend_name_to_enum(attn_backend.get_name())
if attn_backend in {_Backend.FLASH_ATTN, _Backend.FLASH_ATTN_VLLM_V1}: if attn_backend in {_Backend.FLASH_ATTN, _Backend.FLASH_ATTN_VLLM_V1}:
attn_backend = _Backend.XFORMERS attn_backend = _Backend.XFORMERS