ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-03-12 23:10:01 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
d97a6de34d37479f7f989e080aadd6f4350e3f6a
ik_llama.cpp/ggml
History
Kawrakow d97a6de34d Split mode "graph" for Cohere2 (#1061) 
* This works and TG is descent, but PP is low

* Better

* Apply f_logit_scale before mul mat with output tensor

* This is better for PP: 600 t/s -> 700 t/s

* To not lose this again

* WIP

* Equal split

* WIP

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-12-13 20:30:08 +01:00
..
cmake
Merge mainline llama.cpp (#3)
2024-07-27 07:55:01 +02:00
include
Slightly faster TG for split mode "graph" (#1057)
2025-12-12 07:54:37 +01:00
src
Split mode "graph" for Cohere2 (#1061)
2025-12-13 20:30:08 +01:00
.gitignore
Merge mainline llama.cpp (#3)
2024-07-27 07:55:01 +02:00
CMakeLists.txt
Enable fusion by default (#939)
2025-11-11 10:35:48 +02:00