ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-01-26 17:20:01 +00:00
Code Issues Packages Projects Releases Wiki Activity
4,014 Commits 672 Branches 1 Tag
60227f4433949691e4285e635f628ba70a7e3501
Commit Graph

2 Commits

Author SHA1 Message Date
Kawrakow
60227f4433 Make gguf-py stuff work with numpy 2.0 (#991) 
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
 2025-11-20 10:20:55 +01:00
Kawrakow
0ceeb11721 Merge mainline llama.cpp (#3) 
* Merging mainline - WIP

* Merging mainline - WIP

AVX2 and CUDA appear to work.
CUDA performance seems slightly (~1-2%) lower as it is so often
the case with llama.cpp/ggml after some "improvements" have been made.

* Merging mainline - fix Metal

* Remove check

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
 2024-07-27 07:55:01 +02:00