koboldcpp/tools/mtmd
2026-03-30 20:39:55 +08:00
..
debug mtmd: add llama-mtmd-debug binary (#20508) 2026-03-14 15:52:29 +01:00
legacy-models chore : correct typos [no ci] (#20041) 2026-03-05 08:50:21 +01:00
models mtmd: Add DeepSeekOCR Support (#17400) 2026-03-25 19:57:40 +01:00
clip-graph.h mtmd: add clip_graph::build_mm() (#20751) 2026-03-19 13:11:39 +01:00
clip-impl.h warning: clip_image_preprocess has been moved, now you must manually copy init_vision from mtmd into clip.cpp's setup_init_vision_shim_kcpp 2026-03-30 20:39:55 +08:00
clip-model.h mtmd: refactor image preprocessing (#21031) 2026-03-26 19:49:20 +01:00
clip.cpp warning: clip_image_preprocess has been moved, now you must manually copy init_vision from mtmd into clip.cpp's setup_init_vision_shim_kcpp 2026-03-30 20:39:55 +08:00
clip.h prepare for breaking merge 2026-03-29 14:09:29 +08:00
deprecation-warning.cpp Fix locale-dependent float printing in GGUF metadata (#17331) 2026-03-04 09:30:40 +01:00
llava.cpp track clip img patch nx and ny 2025-12-18 22:58:10 +08:00
llava.h track clip img patch nx and ny 2025-12-18 22:58:10 +08:00
mtmd-audio.cpp chore : correct typos [no ci] (#20041) 2026-03-05 08:50:21 +01:00
mtmd-audio.h mtmd: mtmd_audio_streaming_istft (#18645) 2026-01-06 21:00:29 +01:00
mtmd-cli.cpp tools : add missing clocale include in mtmd-cli [no ci] (#20107) 2026-03-04 14:18:04 +01:00
mtmd-helper.cpp note: smartcache is broken for rnn currently 2026-03-15 11:31:47 +08:00
mtmd-helper.h mtmd: add mtmd_log_set (#17268) 2025-11-14 15:56:19 +01:00
mtmd-image.cpp mtmd: refactor image preprocessing (#21031) 2026-03-26 19:49:20 +01:00
mtmd-image.h mtmd: refactor image preprocessing (#21031) 2026-03-26 19:49:20 +01:00
mtmd.cpp mtmd: refactor image preprocessing (#21031) 2026-03-26 19:49:20 +01:00
mtmd.h mtmd : rename mtmd_get_audio_bitrate to mtmd_get_audio_sample_rate (#20105) 2026-03-13 12:30:02 +01:00
requirements.txt requirements : update transformers/torch for Embedding Gemma (#15828) 2025-09-09 06:06:52 +02:00
test-1.jpeg
test-2.mp3 mtmd : support Qwen 2.5 Omni (input audio+vision, no audio output) (#13784) 2025-05-27 14:06:10 +02:00
tests.sh mtmd: Add DeepSeekOCR Support (#17400) 2026-03-25 19:57:40 +01:00