]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: a32b77c)
ggml : support AVX512VNNI (#6280)
authorJustine Tunney <redacted>
Mon, 25 Mar 2024 05:39:56 +0000 (01:39 -0400)
committerGitHub <redacted>
Mon, 25 Mar 2024 05:39:56 +0000 (07:39 +0200)
commit7733f0c76081b2a69b5f8b192db2db7c43629d58
tree2a78e3e47fbd4d768d61f46d06c5c2815640595etree
parenta32b77c4b2c1808654d0b952f26c37d73d2e746bcommit | diff
ggml : support AVX512VNNI (#6280)

This change causes some quants (e.g. Q4_0, Q8_0) to go faster on some
architectures (e.g. AMD Zen 4).
ggml-quants.c diff | blob | history
Packaging of ggml-org/llama.cpp