mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-10-28 17:56:13 +08:00
Yuri KhrustalevandXuan Son Nguyen
4a45de4f2c
* mtmd : lfm2 tiles stretch the image to the grid Lfm2VlImageProcessor.crop_image_to_patches resizes the image straight to (512 * rows, 512 * cols) before it cuts the tiles. llama.cpp kept the aspect ratio and added black bars for LFM2 (only d1-omni stretched), so the tiles of d1-3B and every LFM2-VL / LFM2.5-VL model differed from transformers unless the image had the aspect ratio of the grid. With PAD_NONE the tiles are the same as in transformers. * mtmd : lfm2 layout with Python rounding in double precision Lfm2VlImageProcessor.smart_resize rounds with Python's round (half to even) and computes beta and the tile grid aspect ratio in double. llama.cpp used std::round and float, so 31926 of the 16.7M sizes in [1,4096]^2 got another thumbnail size or grid than transformers (and d1-omni vision.py), e.g. 400x600 -> 416x608 instead of 384x608 and 720x1600 -> 2x5 tiles instead of 2x4. The lfm2 smart resize and grid choice now follow the Python code and match it on every size of that range. * fix --------- Co-authored-by: Xuan Son Nguyen <son@huggingface.co>