Merge mainline llama.cpp (#3)

Browse Source

* 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>

...

This commit is contained in:

Kawrakow

2024-07-27 07:55:01 +02:00

committed by GitHub

parent afd9fd274e

commit 0ceeb11721

612 changed files with 50817 additions and 165936 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

BIN

docs/development/llama-star/idea-arch.key Executable file

Binary file not shown.

BIN

docs/development/llama-star/idea-arch.pdf Normal file

Binary file not shown.