huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-12 12:54:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: return the out tensor rather then the functions return value

Browse Source
This commit is contained in:
drbh 2024-08-05 19:06:55 +00:00
parent dd47a3dac4
commit 516b43f006
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
server/text_generation_server/layers/attention/cuda.py
View File

@ -292,8 +292,7 @@ else:
) )
out = torch.empty_like(q) out = torch.empty_like(q)
flash_attn_cuda.fwd(
return flash_attn_cuda.fwd(
q, q,
k, k,
v, v,
@ -309,4 +308,5 @@ else:
False, False,
0, 0,
None, None,
)[0] )
return out