]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: bf83bff)
metal : enable ggml-alloc (#2627)
authorShouzheng Liu <redacted>
Wed, 16 Aug 2023 20:08:28 +0000 (16:08 -0400)
committerGitHub <redacted>
Wed, 16 Aug 2023 20:08:28 +0000 (23:08 +0300)
commitfc8ef549e50087762a0b4f901cd74b2defcc6ae3
treed15489f213ea892ecb03ca646dcca989584bcfdctree
parentbf83bff6742c0f1795b4c18695a13a34ac7adf62commit | diff
metal : enable ggml-alloc (#2627)

* metal: enable ggml-alloc

Make ggml-alloc work with concurrently dispatch.

* style-fix

Co-authored-by: slaren <redacted>
---------

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