]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 66d403c)
convert : move experts permutation from Qwen2MoeModel to Qwen3VLMoeTextModel (#19445)
authorPiotr Wilkin (ilintar) <redacted>
Tue, 10 Feb 2026 08:01:37 +0000 (09:01 +0100)
committerGitHub <redacted>
Tue, 10 Feb 2026 08:01:37 +0000 (09:01 +0100)
commit854b09f0d7825dd9b8ca542a7f63c2374d66121a
tree6834fa935029543eb33433f953d51864037cc944tree
parent66d403c48098a999406c4850b9d7e6256b73d6dacommit | diff
convert : move experts permutation from Qwen2MoeModel to Qwen3VLMoeTextModel (#19445)

* Add special case for Qwen3VLMoe

* Fix down path, remove arrows and checkmarks

* ws

* Moved to Qwen3VL

* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <redacted>
* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <redacted>
* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <redacted>
---------

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