ik_llama.cpp/ggml.h at ik/glm47_tg_fa_hack - ik_llama.cpp - Public git mirror

ikawrakow/ik_llama.cpp

mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-01-26 17:20:01 +00:00

Files

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

Symbolic link

1 line

22 B

C

Raw Permalink Blame History

../ggml/include/ggml.h