]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
ggml-cpu: ARM64: repack version of q8_0 (dotprod and i8mm) (llama/18096)
authorAlberto Cabrera Pérez <redacted>
Wed, 17 Dec 2025 11:39:13 +0000 (11:39 +0000)
committerGeorgi Gerganov <redacted>
Wed, 31 Dec 2025 10:39:43 +0000 (12:39 +0200)
commit02331aac0a9969b19f8a7aaeff9b46b791b64f88
treeb790441e450b69a367c0df74e606e8d127961dec
parent0b2b21f7390fb10ae779261cb718ff35587a9cdc
ggml-cpu: ARM64: repack version of q8_0 (dotprod and i8mm) (llama/18096)

* wip: skeleton for q8_0 repack

* q8_0 repack GEMV implementations

* GEMM implementations

* Formatting

* Fixed format consistency of repack gemm and gemv declarations

* gemv and gemm generic location consistent with declarations

* Removed non-correct unused variables statements

* Cleanup, consistent style

* Missing generic fallbacks for x86 and powerpc
src/ggml-cpu/arch-fallback.h
src/ggml-cpu/arch/arm/repack.cpp
src/ggml-cpu/repack.cpp
src/ggml-cpu/repack.h