huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 20:34:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

No need to recreate anything actually.

Browse Source
This commit is contained in:
Nicolas Patry 2024-07-01 16:37:36 +00:00
parent ef8bce0b41
commit 1c7c21d596
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
server/text_generation_server/layers/attention/common.py
View File

@ -31,7 +31,8 @@ if FLASH_DECODING:
self.cu_seqlen_k = cu_seqlen_k
def clamp(self, max):
return Seqlen(torch.clamp(self.input_lengths, max=max))
# Flash decoding doesn't need to clamp
return self
else: