ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-24 00:19:19 +00:00
Code Issues Packages Projects Releases Wiki Activity
3,849 Commits 835 Branches 1 Tag
6b6d25bfbf563ee3d30a55815d9a984d05b5306c
Commit Graph

6 Commits

Author SHA1 Message Date
Iwan Kawrakow
6b6d25bfbf llama: factor out model loader 2025-08-13 12:12:46 +03:00
firecoperana
3f111ad7bb add dry sampler (#513) 
* add dry sampler

* use vocab instead of model in dry_init function

* fix compile error for build test

---------

Co-authored-by: firecoperana <firecoperana>
 2025-06-19 10:24:53 +03:00
Kawrakow
a051f08b8f Add copyright notices (#317) 
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
 2025-04-07 10:43:26 +02:00
Kawrakow
1b789c983a Time to fix replace_all (#68) 
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
 2024-09-28 17:59:47 +03:00
Kawrakow
8f43e55103 Merge mainline - Aug 12 2024 (#17) 
* Merge mainline

* Fix after merge

* Remove CI check

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
 2024-08-12 15:14:32 +02:00
Kawrakow
154e0d75fc 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