llama.cpp/tools/mtmd/models
Xuan-Son Nguyen 3d86c6c2b5
model: support GLM4V vision encoder (#18042)
* convert ok

* no deepstack

* less new tensors

* cgraph ok

* add mrope for text model

* faster patch merger

* add GGML_ROPE_TYPE_MRNORM

* add support for metal

* move glm4v do dedicated graph

* convert: add norm_embd

* clip: add debugging fn

* working correctly

* fix style

* use bicubic

* fix mrope metal

* improve cpu

* convert to neox ordering on conversion

* revert backend changes

* force stop if using old weight

* support moe variant

* fix conversion

* fix convert (2)

* Update tools/mtmd/clip-graph.h

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* process mrope_section on TextModel base class

* resolve conflict merge

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2025-12-16 11:25:26 +01:00
..
cogvlm.cpp clip: move model cgraphs into their own files (#17965) 2025-12-12 21:14:48 +01:00
glm4v.cpp model: support GLM4V vision encoder (#18042) 2025-12-16 11:25:26 +01:00
internvl.cpp clip: move model cgraphs into their own files (#17965) 2025-12-12 21:14:48 +01:00
kimivl.cpp clip: move model cgraphs into their own files (#17965) 2025-12-12 21:14:48 +01:00
llama4.cpp clip: move model cgraphs into their own files (#17965) 2025-12-12 21:14:48 +01:00
llava.cpp clip: move model cgraphs into their own files (#17965) 2025-12-12 21:14:48 +01:00
minicpmv.cpp clip: move model cgraphs into their own files (#17965) 2025-12-12 21:14:48 +01:00
models.h model: support GLM4V vision encoder (#18042) 2025-12-16 11:25:26 +01:00
pixtral.cpp clip: move model cgraphs into their own files (#17965) 2025-12-12 21:14:48 +01:00
qwen2vl.cpp clip: move model cgraphs into their own files (#17965) 2025-12-12 21:14:48 +01:00
qwen3vl.cpp clip: move model cgraphs into their own files (#17965) 2025-12-12 21:14:48 +01:00
siglip.cpp clip: move model cgraphs into their own files (#17965) 2025-12-12 21:14:48 +01:00
whisper-enc.cpp model : add glm-asr support (#17901) 2025-12-15 03:18:46 +01:00