Releases: ochafik/llama.cpp
Releases · ochafik/llama.cpp
b4959
convert: fix Mistral3/Gemma3 model hparams init (#12571) * Fix Mistral3/Gemma3 model hparams init * set positional args correctly * use existing hparams if passed
b4943
install : add macports (#12518) MacPorts section added
b4896
llama : fix OLMo-2-0325-32B-Instruct K-norm size (#12400)
b4886
server: fix "--grammar-file" parameter (#12285)
b4865
tests : fix test-quantize-fns to init the CPU backend (#12306) ggml-ci
b4862
`tool-call`: ensure there's always a non-empty tool call id (#12292)
b4855
server : infill gen ends on new line (#12254)
b4828
`tool-call`: fix Qwen 2.5 Coder support, add micro benchmarks, suppor…
b4827
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
sync : ggml ggml-ci