huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-12 04:44:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix non decoding paths.

Browse Source
This commit is contained in:
Nicolas Patry 2024-05-31 22:56:31 +00:00
parent b98b94d695
commit 988aa34f3d
2 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
server/text_generation_server/layers/attention/cuda.py
View File

@ -159,6 +159,7 @@ def paged_attention(
"auto", "auto",
1.0, 1.0,
) )
return out
try: try:

1
server/text_generation_server/layers/attention/rocm.py
View File

@ -129,6 +129,7 @@ def paged_attention(
"auto", "auto",
1.0, 1.0,
) )
return out
if ENGINE != "triton": if ENGINE != "triton":