Gerben van V b4aa7dd477 mtmd : use align_corners for qwen3vl vision position embedding interpolation (#25781) ...

The Qwen3-VL learned position embedding is interpolated to the runtime patch
grid with the default bilinear+antialias (align_corners=False) sampling, while
the transformers reference uses align_corners=True (torch.linspace(0, side-1, T)).
The mismatch scales grounding coordinates about the image center, growing with
image size and per-axis for non-square images (see #16880).

2026-07-21 23:58:34 +02:00

..

cogvlm.cpp

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

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

conformer.cpp

mtmd, server: add "placeholder bitmap" for counting tokens , add */input_tokens API (#23913)

2026-06-06 11:06:51 +02:00

deepseekocr2.cpp

mtmd: Add DeepSeekOCR 2 Support (#20975)

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

deepseekocr.cpp

mtmd: deepseek-ocr v1 multi-tile (#24717)

2026-07-10 16:05:49 +02:00

dotsocr.cpp

mtmd: support dots.ocr (#17575)

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

exaone4_5.cpp

mtmd, server: add "placeholder bitmap" for counting tokens , add */input_tokens API (#23913)

2026-06-06 11:06:51 +02:00

gemma4a.cpp

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

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

gemma4ua.cpp

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

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

gemma4uv.cpp

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

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

gemma4v.cpp

mtmd: add batching API (#24384)

2026-06-13 00:10:29 +02:00

glm4v.cpp

mtmd, server: add "placeholder bitmap" for counting tokens , add */input_tokens API (#23913)

2026-06-06 11:06:51 +02:00

granite4-vision.cpp

model: Granite Speech Plus (#24818)

2026-06-23 12:03:31 +02:00

granite-speech.cpp

model: Granite Speech Plus (#24818)

2026-06-23 12:03:31 +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

mtmd: add batching support for internvl (#24775)

2026-06-19 01:16:16 +02:00

kimik25.cpp

mtmd, server: add "placeholder bitmap" for counting tokens , add */input_tokens API (#23913)

2026-06-06 11:06:51 +02:00

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

model: Granite Speech Plus (#24818)

2026-06-23 12:03:31 +02:00

mimovl.cpp

mtmd, server: add "placeholder bitmap" for counting tokens , add */input_tokens API (#23913)

2026-06-06 11:06:51 +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

mtmd: deepseek-ocr v1 multi-tile (#24717)

2026-07-10 16:05:49 +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 more validations (#25013)

2026-06-26 08:43:29 +02:00

qwen2vl.cpp

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

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

qwen3a.cpp

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

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

qwen3vl.cpp

mtmd : use align_corners for qwen3vl vision position embedding interpolation (#25781)

2026-07-21 23:58:34 +02:00

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, server: add "placeholder bitmap" for counting tokens , add */input_tokens API (#23913)

2026-06-06 11:06:51 +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