Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Fixing intel Supports windowing. (#2637)

This commit is contained in:
Nicolas Patry 2024-10-11 21:47:03 +02:00 committed by GitHub
parent 3dbdf63ec5
commit 0c478846c5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
server/text_generation_server/layers/attention/common.py
View File

@ -68,5 +68,5 @@ else:
def clamp(self, max): def clamp(self, max):
if SYSTEM == "rocm": if SYSTEM == "rocm":
return self return self
raise NotImplementedError("Not implemented seqlen for paged") self.input_lengths = torch.clamp(self.input_lengths, max=max)
return Seqlen(torch.clamp(self.input_lengths, max=max)) return self