onnxruntime
Fix GQA Rotary Embedding sequence length
#19801
Merged

Fix GQA Rotary Embedding sequence length #19801

aciddelgado merged 1 commit into main from aciddelgado/fix_rotary_gqa
aciddelgado
aciddelgado modify rotary cache dim check
b43de5ef
aciddelgado aciddelgado requested a review from kunal-vaishnavi kunal-vaishnavi 2 years ago
aciddelgado aciddelgado requested a review from yufenglee yufenglee 2 years ago
kunal-vaishnavi
kunal-vaishnavi approved these changes on 2024-03-06
aciddelgado aciddelgado merged 8bd1335d into main 2 years ago
aciddelgado aciddelgado deleted the aciddelgado/fix_rotary_gqa branch 2 years ago
kunal-vaishnavi kunal-vaishnavi added release:1.17.3

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone