]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 3a00c98)
ggml-cpu: FA add GEMM microkernel (#19422)
authorAman Gupta <redacted>
Sun, 15 Feb 2026 05:39:24 +0000 (11:09 +0530)
committerGitHub <redacted>
Sun, 15 Feb 2026 05:39:24 +0000 (11:09 +0530)
commit684b36101c9eeb7e89c9e602f9ded05f1353a0c6
tree0894b9e30fde28e53dfed9b8fc0d9ef35879e6f1tree
parent3a00c98584e42a20675b6569d81beadb282b0952commit | diff
ggml-cpu: FA add GEMM microkernel (#19422)

* ggml-cpu: FA add GEMM microkernel

* add guard for sizeless vector types

* fix case where DV % GGML_F32_EPR !=0

* move memset out of the loop

* move another memset out of the loop

* use RM=4 for arm

* simd_gemm: convert everything to int

* convert everything to size_t to avoid warnings

* fixup

* add pragma for ignoring aggressive loop optimizations
ggml/src/ggml-cpu/common.h diff | blob | history
ggml/src/ggml-cpu/ggml-cpu.c diff | blob | history
ggml/src/ggml-cpu/ops.cpp diff | blob | history
ggml/src/ggml-cpu/simd-gemm.h [new file with mode: 0644] blob
Packaging of ggml-org/llama.cpp