]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 2e2d99c)
llama: Restore quantization of mmprojs (#26818)
authorPedro Cuenca <redacted>
Mon, 10 Aug 2026 09:58:32 +0000 (11:58 +0200)
committerGitHub <redacted>
Mon, 10 Aug 2026 09:58:32 +0000 (11:58 +0200)
commit86c298fb8ac1ee9da24e3c4d68b71b1247dc151a
tree3d5d50a6f36e045a85f7d20ca1b8c26a5141ad3ftree
parent2e2d99cfd27d8bab08b6ee36836e20979ba48445commit | diff
llama: Restore quantization of mmprojs (#26818)

* Restore quantization of mmprojs

This was lost in the refactor undertaken in #22004.

* add noreturn

---------

Co-authored-by: Xuan Son Nguyen <redacted>
src/llama-model.cpp diff | blob | history
src/models/clip.cpp [new file with mode: 0644] blob
src/models/models.h diff | blob | history
Packaging of ggml-org/llama.cpp