Add packed QKV and rotary embedding within GroupQueryAttention to model builder#245
Merged
natke merged 14 commits intomainfrom kvaishnavi/rotemb-in-gqaApr 8, 2024
+168-103
Commits
Commits on Mar 9, 2024
Commits on Mar 11, 2024
Commits on Mar 14, 2024
Commits on Mar 15, 2024
Commits on Mar 20, 2024
Commits on Apr 1, 2024
- committed
- committed
- committed
- committed
- committed
- committed
- committed