This website requires JavaScript.
Explore
Help
Sign In
nicolas
/
ik_llama_opt
Watch
1
Star
0
Fork
You've already forked ik_llama_opt
0
Code
Issues
Pull Requests
Packages
Projects
Releases
Wiki
Activity
088a8360a1
ik_llama_opt
/
ggml
History
Kawrakow
088a8360a1
iq3_k: slightly faster Metal dequantize kernel
...
PP-512 goes to 473 t/s up from 452 t/s.
2024-08-01 09:38:06 +02:00
..
cmake
Merge mainline llama.cpp (
#3
)
2024-07-27 07:55:01 +02:00
include
iq3_k: Basics
2024-08-01 09:38:06 +02:00
src
iq3_k: slightly faster Metal dequantize kernel
2024-08-01 09:38:06 +02:00
.gitignore
Merge mainline llama.cpp (
#3
)
2024-07-27 07:55:01 +02:00
CMakeLists.txt
Merge mainline llama.cpp (
#3
)
2024-07-27 07:55:01 +02:00
Powered by
TurnKey Linux
.