rlx-dinov2 0.2.6

DINOv2 ViT encoder for RLX
Documentation

DINOv2 — Meta's self-supervised ViT (with optional registers).

Public entry points:

  • [DinoV2Config] — model dimensions + variant factories (vit_small, vit_base, vit_large)
  • [build_dinov2_graph_sized] — emits the IR graph and the host-side [DinoV2PreprocessWeights].
  • [assemble_hidden] / [rgb_u8_to_imagenet_nchw] — host-side image → encoder-input plumbing.

Weight keys match Meta / candle's safetensors so checkpoints from the HF Hub (e.g. lmz/candle-dino-v2) load with no remapping.