mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-08-29 00:20:49 +02:00
b4aa7dd477
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).