Add LLaMA GQA ragged batching #18337
Fix GQA ragged batching
7ccec207
Remove GQA left padding fix
645225ec
Add changes suggested by linter
21fd8559
Merge branch 'main' into kvaishnavi/llama-fix-gqa-batching
1eabc508
Update README
d1b5511b
yufenglee
approved these changes
on 2023-11-08
tianleiwu
merged
c8def0cc
into main 2 years ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub