Junwon HwangandLG-AI-EXAONE 48b88c3b00 model: Add EXAONE 4.5 implementations (#21733) ...

* Add EXAONE 4.5 and Add GQA for MMproj

* mtmd: EXAONE 4.5 vision markers and projector path

EXAONE 4.5 uses <vision> and </vision> for image boundaries; Qwen keeps
<|vision_start|> and <|vision_end|>.

Route EXAONE 4.5 through the Qwen2.5-VL-style encode path (window attention
pattern, optional mmproj input norm). Update exaone4_5 projector weights and
convert_hf_to_gguf for mmproj export.

* mtmd: load EXAONE4 nextn tensors correctly

Align EXAONE4 tensor registration with EXAONE_MOE for NextN/MTP slots and avoid skip-flag propagation on duplicated rope_freqs so model loading succeeds for EXAONE 4.5 GGUF.

* Minor fixes

* Address PR feedback

* Address PR feedback

* Fix EXAONE after merge

* Fix EXAONE 4.5 conversion

* Address PR feedback

* Refactor EXAONE 4.5 conversion

* Address PR feedback

* Fix unintended deletion

* Minor fix

---------

Co-authored-by: LG-AI-EXAONE <exaonemodels@lgresearch.ai>

2026-06-01 11:48:53 +02:00

..

cogvlm.cpp

mtmd: add clip_graph::build_mm() (#20751)

2026-03-19 13:11:39 +01:00

conformer.cpp

mtmd: add clip_graph::build_mm() (#20751)

2026-03-19 13:11:39 +01:00

deepseekocr2.cpp

mtmd: Add DeepSeekOCR 2 Support (#20975)

2026-05-29 16:13:51 +02:00

deepseekocr.cpp

mtmd: Add DeepSeekOCR 2 Support (#20975)

2026-05-29 16:13:51 +02:00

dotsocr.cpp

mtmd: support dots.ocr (#17575)

2026-04-09 12:16:38 +02:00

exaone4_5.cpp

model: Add EXAONE 4.5 implementations (#21733)

2026-06-01 11:48:53 +02:00

gemma4a.cpp

mtmd: add Gemma 4 audio conformer encoder support (#21421)

2026-04-12 14:15:26 +02:00

gemma4v.cpp

mtmd: fix gemma 4 projector pre_norm (#23822)

2026-05-28 20:58:55 +02:00

glm4v.cpp

mtmd: Add DeepSeekOCR Support (#17400)

2026-03-25 19:57:40 +01:00

granite-speech.cpp

mtmd: add granite-speech support (ibm-granite/granite-4.0-1b-speech) (#22101)

2026-05-06 14:40:59 +02:00

hunyuanvl.cpp

mtmd, model : merge HunyuanOCR into HunyuanVL and fix OCR vision precision (#23329)

2026-05-21 00:35:37 +02:00

internvl.cpp

clip: move model cgraphs into their own files (#17965)

2025-12-12 21:14:48 +01:00

kimik25.cpp

model: Add Kimi-K2.5 support (#19170)

2026-02-11 16:47:30 +01:00

kimivl.cpp

clip: move model cgraphs into their own files (#17965)

2025-12-12 21:14:48 +01:00

llama4.cpp

mtmd: add clip_graph::build_mm() (#20751)

2026-03-19 13:11:39 +01:00

llava.cpp

mtmd: add clip_graph::build_mm() (#20751)

2026-03-19 13:11:39 +01:00

mimovl.cpp

mtmd: add MiMo v2.5 vision (#22883)

2026-05-12 11:11:14 +02:00

minicpmv.cpp

mtmd : support MiniCPM-V 4.6 (#22529)

2026-05-06 21:54:09 +02:00

mobilenetv5.cpp

mtmd: add clip_graph::build_mm() (#20751)

2026-03-19 13:11:39 +01:00

models.h

model: Add EXAONE 4.5 implementations (#21733)

2026-06-01 11:48:53 +02:00

nemotron-v2-vl.cpp

mtmd : Add Nemotron Nano 12B v2 VL support (#19547)

2026-02-14 14:07:00 +01:00

paddleocr.cpp

model: Add PaddleOCR-VL model support (#18825)

2026-02-19 17:05:25 +01:00

pixtral.cpp

mtmd: add clip_graph::build_mm() (#20751)

2026-03-19 13:11:39 +01:00

qwen2vl.cpp

mtmd: add clip_graph::build_mm() (#20751)

2026-03-19 13:11:39 +01:00

qwen3a.cpp

mtmd: add chunks and fix preproc for qwen3a (#23073)

2026-05-15 19:32:47 +02:00

qwen3vl.cpp

mtmd: add clip_graph::build_mm() (#20751)

2026-03-19 13:11:39 +01:00

siglip.cpp

mtmd: Add DeepSeekOCR Support (#17400)

2026-03-25 19:57:40 +01:00

step3vl.cpp

model : support step3-vl-10b (#21287)

2026-04-08 09:51:31 +02:00

whisper-enc.cpp

mtmd : add MERaLiON-2 multimodal audio support (#21756)

2026-04-11 14:15:48 +02:00

yasa2.cpp

mtmd: Add support for Reka Edge 2603 (#21616)

2026-04-21 20:02:49 +02:00

youtuvl.cpp

mtmd: add clip_graph::build_mm() (#20751)

2026-03-19 13:11:39 +01:00