Concedo a860ec0b37 Merge branch 'upstream' into concedo_experimental ...

# Conflicts:
#	.github/workflows/winget.yml

2026-06-10 23:16:06 +08:00

..

debug

Merge branch 'upstream' into concedo_experimental

2026-05-30 01:54:53 +08:00

legacy-models

chore : correct typos [no ci] (#20041)

2026-03-05 08:50:21 +01:00

models

mtmd: support "frame merge" for qwen-vl-based models (#21858)

2026-06-06 21:17:25 +02:00

tests

mtmd: Add DeepSeekOCR 2 Support (#20975)

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

clip-graph.h

mtmd: support "frame merge" for qwen-vl-based models (#21858)

2026-06-06 21:17:25 +02:00

clip-impl.h

Merge branch 'upstream' into concedo_experimental

2026-06-10 00:36:26 +08:00

clip-model.h

model, mtmd: Granite4 Vision (#23545)

2026-06-05 17:44:59 +02:00

clip.cpp

Merge branch 'upstream' into concedo_experimental

2026-06-10 17:21:05 +08:00

clip.h

fix build, remove clip quantize (+1 squashed commits)

2026-06-10 00:42:34 +08:00

deprecation-warning.cpp

Fix locale-dependent float printing in GGUF metadata (#17331)

2026-03-04 09:30:40 +01:00

llava.h

updated to handle changes for clip_is_mrope

2026-04-21 19:34:32 +08:00

mtmd-audio.cpp

mtmd, model: allow skip build_vit() (#24077)

2026-06-03 17:10:35 +02:00

mtmd-audio.h

mtmd, model: allow skip build_vit() (#24077)

2026-06-03 17:10:35 +02:00

mtmd-cli.cpp

mtmd : add video input support (#24269)

2026-06-08 14:40:12 +03:00

mtmd-helper.cpp

Merge branch 'upstream' into concedo_experimental

2026-06-10 17:21:05 +08:00

mtmd-helper.h

mtmd : add video input support (#24269)

2026-06-08 14:40:12 +03:00

mtmd-image.cpp

mtmd: support "frame merge" for qwen-vl-based models (#21858)

2026-06-06 21:17:25 +02:00

mtmd-image.h

mtmd: Add DeepSeekOCR 2 Support (#20975)

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

mtmd.cpp

Merge branch 'upstream' into concedo_experimental

2026-06-10 17:21:05 +08:00

mtmd.h

Merge branch 'upstream' into concedo_experimental

2026-06-10 17:21:05 +08:00

requirements.txt

requirements : bump torch to 2.11.0 (#23503)

2026-05-23 18:24:39 +02:00

test-1.jpeg

mtmd : rename llava directory to mtmd (#13311)

2025-05-05 16:02:55 +02:00

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

graph: Fix granite speech model inference by applying embedding scale when deepstack is not used (#24357)

2026-06-09 19:46:27 +02:00