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

rocm ck flash attn api fix

Browse Source
This commit is contained in:
seungrokjung 2024-06-05 12:45:53 +00:00
parent 8aece3bd68
commit 1b53c70523
1 changed files with 1 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
server/text_generation_server/layers/attention/rocm.py
View File

@ -186,17 +186,12 @@ if ENGINE == "ck":
out, out,
cu_seqlens, cu_seqlens,
cu_seqlens, cu_seqlens,
None,
None,
None,
max_s, max_s,
max_s, max_s,
0.0, 0.0,
softmax_scale, softmax_scale,
False, False,
causal, True,
window_size_left,
0,
False, False,
None, None,
) )