llama.cpp
47d52b2b
- Q2_K: fixed bug in imatrix quantization for QK_K = 64
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
1 year ago
Q2_K: fixed bug in imatrix quantization for QK_K = 64
References
#5760 - Make i-quants work with super-blocks of 64 (CPU and Metal)
Author
Iwan Kawrakow
Parents
2540a290
Loading