PR #1866 gguf format add support for mtp quantization

gguf format support for mtp quantization

n1ck-guo committed 72 days ago

fix ut

n1ck-guo committed 71 days ago

Merge branch 'main' into hengguo/gguf_mtp

n1ck-guo committed 71 days ago

update gguf export

n1ck-guo committed 71 days ago

Merge branch 'hengguo/gguf_mtp' of https://github.com/intel/auto-round

n1ck-guo committed 71 days ago

Merge remote-tracking branch 'origin/main' into hengguo/gguf_mtp

n1ck-guo committed 71 days ago

fix ut

n1ck-guo committed 71 days ago

fix some issues

wenhuach21 committed 68 days ago

[pre-commit.ci] auto fixes from pre-commit.com hooks

pre-commit-ci[bot] committed 68 days ago

fix gguf export

n1ck-guo committed 67 days ago

merge main

n1ck-guo committed 67 days ago

update q2k_mixed recipe

n1ck-guo committed 67 days ago

fix ut

n1ck-guo committed 66 days ago

Merge branch 'main' into hengguo/gguf_mtp

n1ck-guo committed 66 days ago

auto-round gguf format add support for mtp quantization #1866 Merged