mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-08-26 00:34:30 +00:00
48b88c3b00
* 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> |
||
|---|---|---|
| .. | ||
| cogvlm.cpp | ||
| conformer.cpp | ||
| deepseekocr.cpp | ||
| deepseekocr2.cpp | ||
| dotsocr.cpp | ||
| exaone4_5.cpp | ||
| gemma4a.cpp | ||
| gemma4v.cpp | ||
| glm4v.cpp | ||
| granite-speech.cpp | ||
| hunyuanvl.cpp | ||
| internvl.cpp | ||
| kimik25.cpp | ||
| kimivl.cpp | ||
| llama4.cpp | ||
| llava.cpp | ||
| mimovl.cpp | ||
| minicpmv.cpp | ||
| mobilenetv5.cpp | ||
| models.h | ||
| nemotron-v2-vl.cpp | ||
| paddleocr.cpp | ||
| pixtral.cpp | ||
| qwen2vl.cpp | ||
| qwen3a.cpp | ||
| qwen3vl.cpp | ||
| siglip.cpp | ||
| step3vl.cpp | ||
| whisper-enc.cpp | ||
| yasa2.cpp | ||
| youtuvl.cpp | ||