]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 6b10a82)
vulkan: use graphics queue on AMD (#20551)
authorRuben Ortlam <redacted>
Sun, 15 Mar 2026 07:18:54 +0000 (08:18 +0100)
committerGitHub <redacted>
Sun, 15 Mar 2026 07:18:54 +0000 (08:18 +0100)
commit1a3d8edbbaba7f6e36096982c7c8a7ce11f4a7e8
tree4664f380ad4721670ff4cd318396cc87aba602b4tree
parent6b10a82c00064d4ead889b09d7fae9eff6927d57commit | diff
vulkan: use graphics queue on AMD (#20551)

* vulkan: use graphics queue on AMD for slightly better performance

* disable async transfer queue on AMD
ggml/src/ggml-vulkan/ggml-vulkan.cpp diff | blob | history
Packaging of ggml-org/llama.cpp