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

Update server/text_generation_server/layers/attention/xpu.py

Browse Source
This commit is contained in:
Nicolas Patry 2024-05-31 17:56:08 +02:00 committed by GitHub
parent d44688b6ac
commit b0c168d249
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -14,9 +14,6 @@ def attention(
softmax_scale, softmax_scale,
window_size_left=-1, window_size_left=-1,
): ):
if window_size_left <= 0 and window_size_left != -1:
raise ValueError("`window_size_left` must be > 0 or -1")
if window_size_left != -1: if window_size_left != -1:
raise ValueError( raise ValueError(
f"XPU version of Flash Attention does not support window attention (window_size_left != -1, got window_size_left={window_size_left})." f"XPU version of Flash Attention does not support window attention (window_size_left != -1, got window_size_left={window_size_left})."