]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: adc5dd9)
ggml: aarch64: implement SVE kernels for q4_K_q8_K vector dot (#11227)
authorfj-y-saito <redacted>
Thu, 16 Jan 2025 09:11:49 +0000 (18:11 +0900)
committerGitHub <redacted>
Thu, 16 Jan 2025 09:11:49 +0000 (11:11 +0200)
commitc67cc9837d48ea7f612b5666b90d189e63dfd7d3
tree45cde1d271cfc0aea3eb37e37fadf467aae2289btree
parentadc5dd92e8aea98f5e7ac84f6e1bc15de35130b5commit | diff
ggml: aarch64: implement SVE kernels for q4_K_q8_K vector dot (#11227)

* Add SVE support for q4_K_q8_K

* Update ggml/src/ggml-cpu/ggml-cpu-quants.c

change to use K_SCALE_SIZE

Co-authored-by: Georgi Gerganov <redacted>
---------

Co-authored-by: Georgi Gerganov <redacted>
ggml/src/ggml-cpu/ggml-cpu-quants.c diff | blob | history
Packaging of ggml-org/llama.cpp