]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
ggml-cpu: aarm64: q4_K repack gemm and gemv implementations (dotprod only) (llama...
authorAlberto Cabrera Pérez <redacted>
Thu, 27 Nov 2025 11:25:14 +0000 (11:25 +0000)
committerGeorgi Gerganov <redacted>
Thu, 11 Dec 2025 13:32:47 +0000 (15:32 +0200)
commit00cc47e7553b9e97c2e5efd73b808e42cfb29d64
tree8d1503624d1325596778fe42b5860c2c34d44ea1
parent37bfc637f56ce339ac7447bcb432ed0d49bd775c
ggml-cpu: aarm64: q4_K repack gemm and gemv implementations (dotprod only) (llama/17494)

* Enabled q4_K_4x8 path

* Fixed generic Q4_K 8x4 implementation

* wip: dotprod gemm

* Working arm q4_K dotprod gemm

Signed-off-by: Alberto Cabrera <redacted>
* Undo acc rename

Signed-off-by: Alberto Cabrera <redacted>
* Q4_K arm dotprod gemm

Signed-off-by: Alberto Cabrera <redacted>
* Fix: q4_qs reinterpret from uint to int

Signed-off-by: Alberto Cabrera <redacted>
* Removed comments

* Fixed macro guards

* Fixed unused vars in generic implementation

* Fixed unused vars in 8x4 repack

* Fixed unused vars in generic implementation, unneeded comment

* Missing arch fallback for x86

* minor : style

---------

Signed-off-by: Alberto Cabrera <redacted>
Co-authored-by: Georgi Gerganov <redacted>
src/ggml-cpu/arch-fallback.h
src/ggml-cpu/arch/arm/repack.cpp
src/ggml-cpu/repack.cpp
src/ggml-cpu/repack.h