transformers
75e39856
- Fix Break change of AWQ FusedModules due to Attention Refactor (#41909)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
158 days ago
Fix Break change of AWQ FusedModules due to Attention Refactor (#41909) * fix awq bc due to attention refactor * feat: support more rope_types for awq fusion * feat: add test for llama3 * fix ruff format * propagate changes in modeling_llama
References
#41909 - Fix Break change of AWQ FusedModules due to Attention Refactor
Author
fanqiNO1
Parents
61cafd99
Loading