llama.cpp
245fc3c3
- metal : faster q4_0 (#1775)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
2 years ago
metal : faster q4_0 (#1775) * metal : 8% faster q4_0 Avoid copying into local uchar4 anf float4. * metal : 17% faster Q4_0 Use 64 threads in a thread group. --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
References
#1775 - metal : faster q40
Author
ikawrakow
Parents
72ff5282
Loading