llama.cpp
45155597
- add fast matmul iquants (#22504)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
10 days ago
add fast matmul iquants (#22504)
References
#22504 - ggml-webgpu: add fast mat-mat path for i-quants
Author
SharmaRithik
Parents
80afa33a
Loading
