Fix Break change of AWQ FusedModules due to Attention Refactor #41909
fix awq bc due to attention refactor
63d7ca37
feat: support more rope_types for awq fusion
1f49232b
feat: add test for llama3
9cdc8080
fix ruff format
6d2fa278
SunMarc
approved these changes
on 2025-11-14
propagate changes in modeling_llama
e8d3a215
MekkCyber
approved these changes
on 2025-11-19
SunMarc
merged
75e39856
into main 204 days ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub