llama.cpp/ggml/src/ggml-cpu/arch
Alberto Cabrera Pérez 669696e00d
ggml-cpu: ARM64: repack version of q8_0 (dotprod and i8mm) (#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
2025-12-17 13:39:13 +02:00
..
arm ggml-cpu: ARM64: repack version of q8_0 (dotprod and i8mm) (#18096) 2025-12-17 13:39:13 +02:00
loongarch ggml : LoongArch fixes (#16958) 2025-11-03 08:40:02 +02:00
powerpc ggml-cpu: add mxfp4 VSX intrinsics for Power9+ (ppc64le) hardware (#15385) 2025-08-19 11:54:31 +03:00
riscv ggml: replace hwcap with riscv_hwprobe for RVV detection (#17567) 2025-11-29 14:56:31 +02:00
s390 ggml: add s390x cpu-feats (#16774) 2025-11-02 08:48:23 +08:00
wasm ggml-cpu : deduplicate scalar implementations (#14897) 2025-07-28 17:40:24 +02:00
x86 ggml : add missing AVX512 feature checks (#17270) 2025-11-17 12:12:00 +01:00