DINOv2 linear

• Original code: https://github.com/facebookresearch/dinov2 at 7764ea0f912e
• Code licence: Apache-2.0 (permissive); files:
• Weights licence: Apache-2.0
• Licence evidence: https://github.com/facebookresearch/dinov2/blob/7764ea0f912e53c92e82eb78a2a1631e92725fc8/README.md#L660
• Training data: LVD-142M (DINOv2's curated web-image set, not released), ADE20K (SceneParsing, 150 classes)
• Kernel libraries: fastbb, seg_up
• Variants: dinov2-s-linear-ade20k, dinov2-b-linear-ade20k, dinov2-l-linear-ade20k
• Outputs: logits; label_set: ade20k-150
• Input size: any H x W >= 1, resized or padded inside the model
• Tested up to (portable, fp16, RTX 5060 Ti 16 GB): dinov2-s-linear-ade20k 3000x4000 (7.2 GiB peak allocated, 7.9 reserved); dinov2-b-linear-ade20k 3000x4000 (7.3 GiB peak allocated, 8.1 reserved); dinov2-l-linear-ade20k 3000x4000 (7.7 GiB peak allocated, 8.5 reserved)
• dinov2-s-linear-ade20k 1024x2048, first call: portable + torch.compile 11 s (cold Inductor cache), TensorRT fp16 36 s (ONNX + engine).
• dinov2-s-linear-ade20k original 1024x2048: torch.autocast(fp16) around the forward
• dinov2-b-linear-ade20k original 1024x2048: torch.autocast(fp16) around the forward
• dinov2-l-linear-ade20k original 1024x2048: torch.autocast(fp16) around the forward
• dinov2-s-linear-ade20k load / first call: original 4.02 s / 0.303 s (512x512), portable 0.12 s / 0.09 s, kernels 0.23† s / 0.061† s
• dinov2-b-linear-ade20k load / first call: original 12.01 s / 0.016 s (512x512), portable 0.27 s / 0.105 s, kernels 0.4† s / 0.071† s
• dinov2-l-linear-ade20k load / first call: original 7.86 s / 0.382 s (512x512), portable 0.81 s / 0.156 s, kernels 0.92† s / 0.103† s
• † measured in the speed sweep after the portable load (or an earlier size) in the same process: file cache and kernels are warm, so the time is lower than a fresh start.
• Protocol, first call, 3 warm-up, peak reset, median of 3 rounds x median of 5 (tools/speed_check.py), synthetic CUDA input (bench_inputs); peak = max over the first call and the timed calls

Measured

Each image at its own size, argmax of the logits. Original = the original code named under Details, same checkpoint and protocol.

Measured on NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks 939adfe8, 2026-11-06.

Parity

CPU, float32: max |diff| <= 0.002 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.05 and p99 <= 0.25 (absolute error of the output logits).