llama.cpp
17acbc52
- cont : drop Q4_0 ne11=2 special-case
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
40 days ago
cont : drop Q4_0 ne11=2 special-case
References
#29869 - metal : few-row MMA mat-mul and batched copies for speculative decoding
Author
ggerganov
Parents
3af8f157
Loading