auto-round
0880b1e4
- fix(rrq): implement RTN quantization for layers outside transformer blocks
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
10 days ago
fix(rrq): implement RTN quantization for layers outside transformer blocks
References
#2308 - Recurrent Residual Quantization (RRQ) for LLMs
Author
luoyu-intel
Committer
luoyu-intel
Parents
a8aad39d
Loading