]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 1117d06)
metal : implement q5_0 and q5_1 kernels (#3648)
authorJhen-Jie Hong <redacted>
Wed, 18 Oct 2023 12:21:48 +0000 (07:21 -0500)
committerGitHub <redacted>
Wed, 18 Oct 2023 12:21:48 +0000 (15:21 +0300)
commitc67fe68e417f766970fb1feaf2e66458aa24116a
tree0146618767b8b9ae811a233814bf3a217784a55btree
parent1117d06607d2d885640ac501f05f0aae5494e2c5commit | diff
metal : implement q5_0 and q5_1 kernels (#3648)

* metal : implement dequantize_q5_0

* metal : block_q_n_dot_y for block_q5_0 (broken)

* metal : revert unnecessary change

* metal : implement dequantize_q5_1

* metal : block_q_n_dot_y for q5_1 (broken)

* metal : fix block_q_n_dot_y

* minor : spaces / formatting

---------

Co-authored-by: Georgi Gerganov <redacted>
ggml-metal.m diff | blob | history
ggml-metal.metal diff | blob | history
Packaging of ggml-org/llama.cpp