]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 516a4ca)
model : clean up and fix EXAONE-MoE configuration (#18840)
authorJunwon Hwang <redacted>
Wed, 14 Jan 2026 18:38:21 +0000 (03:38 +0900)
committerGitHub <redacted>
Wed, 14 Jan 2026 18:38:21 +0000 (19:38 +0100)
commit8fb717557638f819e668e87f6d7dc0f39eb09c68
treefcc5a399d495d5b46fc644f21d7d67082273cfbctree
parent516a4ca9b5f2fa72c2a71f412929a67cf76a6213commit | diff
model : clean up and fix EXAONE-MoE configuration (#18840)

* Fix mismatch of EXAONE-MoE configuration

* ensure gating func is set, cleanup

---------

Co-authored-by: Sigbjørn Skjæret <redacted>
convert_hf_to_gguf.py diff | blob | history
src/llama-model.cpp diff | blob | history
Packaging of ggml-org/llama.cpp