Releases: pwilkin/llama.cpp
Releases · pwilkin/llama.cpp
b5940
Merge branch 'ggml-org:master' into master
b5937
Merge branch 'ggml-org:master' into master
b5897
Fix non-MoE regression Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
b5896
Code style from code review Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
b5894
Fix trailing whitespace
b5893
Further fixes from code review
b5892
Apply suggestions from code review Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
b5891
Add unit32 cast for Linux builds
b5882
CUDA: add set rows for f32 and f16 (#14551) * CUDA: add set rows for f32 and f16 * Review: change kernel params, use strides from host * Use 1-d kernel * Review: use int64_t for blockDim.x, rename nb->s for clarity