Skip to content

Releases: ochafik/llama.cpp

b4959

26 Mar 00:41
53af4db

Choose a tag to compare

convert: fix Mistral3/Gemma3 model hparams init (#12571)

* Fix Mistral3/Gemma3 model hparams init

* set positional args correctly

* use existing hparams if passed

b4943

23 Mar 12:24
18b663d

Choose a tag to compare

install : add macports (#12518)

MacPorts section added

b4896

16 Mar 22:53
8ba95dc

Choose a tag to compare

llama : fix OLMo-2-0325-32B-Instruct K-norm size (#12400)

b4886

14 Mar 12:00
add2a3a

Choose a tag to compare

server: fix "--grammar-file" parameter (#12285)

b4865

10 Mar 13:53
e128a1b

Choose a tag to compare

tests : fix test-quantize-fns to init the CPU backend (#12306)

ggml-ci

b4862

10 Mar 10:26
be421fc

Choose a tag to compare

`tool-call`: ensure there's always a non-empty tool call id (#12292)

b4855

08 Mar 15:10
7ab3643

Choose a tag to compare

server : infill gen ends on new line (#12254)

b4828

05 Mar 13:47
669912d

Choose a tag to compare

`tool-call`: fix Qwen 2.5 Coder support, add micro benchmarks, suppor…

b4827

05 Mar 11:24
fa31c43

Choose a tag to compare

ci : fix xcframework artifact tag (#12191)

The commit add the name parameter to the upload-artifact action to
ensure that the artifact is uploaded with the correct name.

The motivation for this is that currently the uploaded xcframework
is named as llama-b1-xcframework.zip. With this change the name of this
artifact should contain the build number like the other artifacts.

b4818

03 Mar 21:48

Choose a tag to compare

sync : ggml

ggml-ci