]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: c5b0f4b)
ggml : add Q4_0_8_8 RISC-V GEMV and GEMM kernels (#10029)
authorxctan <redacted>
Wed, 30 Oct 2024 07:00:40 +0000 (15:00 +0800)
committerGitHub <redacted>
Wed, 30 Oct 2024 07:00:40 +0000 (09:00 +0200)
commitfc83a9e58479e4dd70054daa7afe5184c1bbe545
treeefce16280e80aae5c34f2b9eb16ada0dcfe58bc9tree
parentc5b0f4b5d90297f3e729fca7f78ddb25fcab5ddccommit | diff
ggml : add Q4_0_8_8 RISC-V GEMV and GEMM kernels (#10029)

* ggml : RISC-V vector gemv for q4_0_8x8

* ggml : Added WIP rvv q4_0_8x8 gemm

* ggml : Added initial implementation of rvv gemm

* ggml : optimize gemm to avoid register spillover

* ggml : Fix GCC rvv load alignment issue

* ggml : Format gemm rvv code

* ggml : Fix a typo in RVV q4_0_8_8 GEMM
ggml/src/ggml-aarch64.c diff | blob | history
Packaging of ggml-org/llama.cpp