huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 04:14:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix default window size

Browse Source
This commit is contained in:
OlivierDehaene 2023-09-28 09:24:32 +02:00
parent f938825272
commit 8a3449def9
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
server/text_generation_server/utils/flash_attn.py
View File

@ -57,7 +57,7 @@ def attention(
cu_seqlens, cu_seqlens,
max_s, max_s,
softmax_scale, softmax_scale,
window_size_left=0, window_size_left=-1,
): ):
if HAS_FLASH_ATTN_V2: if HAS_FLASH_ATTN_V2:
return flash_attn_2_cuda.varlen_fwd( return flash_attn_2_cuda.varlen_fwd(