llama.cpp
0ee322cd
- Merge branch 'master' into compilade/imatrix-batched-chunks
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
116 days ago
Merge branch 'master' into compilade/imatrix-batched-chunks
References
#9400 - imatrix : use GGUF to store importance matrices
Author
compilade
Parents
e33de128
c31e6064
Loading
