DINOv2

• Original code: https://github.com/facebookresearch/dinov2 at 7764ea0
• Code licence: Apache-2.0 (permissive); files: LICENSE
• Weights licence: Apache-2.0
• Licence evidence: https://github.com/facebookresearch/dinov2/blob/7764ea0/README.md (License section: code and model weights under Apache 2.0)
• Training data: LVD-142M: 142M images retrieved from web crawls by similarity to curated datasets (ImageNet-22k/1k train, Google Landmarks, fine-grained sets), self-supervised (no labels), per the paper; not released
• Options: fp16_accumulate = False (precision only)
• Kernel libraries: fastbb
• Variants: dinov2-vits14, dinov2-vits14-reg, dinov2-vitb14, dinov2-vitb14-reg, dinov2-vitl14, dinov2-vitl14-reg, dinov2-vitg14, dinov2-vitg14-reg
• Outputs: last_hidden_state, pooler_output, hidden_states
• Input size: any H x W >= 1, resized or padded inside the model
• Tested up to (portable, fp16, RTX 5060 Ti 16 GB): dinov2-vits14 3000x4000 (0.8 GiB peak allocated, 1.2 reserved); dinov2-vits14-reg 3000x4000 (0.8 GiB peak allocated, 1.2 reserved); dinov2-vitb14 3000x4000 (1.4 GiB peak allocated, 2.2 reserved); dinov2-vitb14-reg 3000x4000 (1.4 GiB peak allocated, 2.2 reserved); dinov2-vitl14 3000x4000 (2.2 GiB peak allocated, 3.1 reserved); dinov2-vitl14-reg 3000x4000 (2.2 GiB peak allocated, 3.1 reserved); dinov2-vitg14 3000x4000 (4.8 GiB peak allocated, 5.9 reserved); dinov2-vitg14-reg 3000x4000 (4.8 GiB peak allocated, 5.9 reserved)
• dinov2-vitb14 224x224, first call: portable + torch.compile 10 s (cold Inductor cache), TensorRT fp16 25 s (ONNX + engine).
• dinov2-vits14 original 224x224: torch.autocast(fp16) around the forward
• dinov2-vits14-reg original (fp32) 224x224, original 224x224: dinov2 forward_features CLS
• dinov2-vitb14 original 224x224: torch.autocast(fp16) around the forward
• dinov2-vitb14-reg original 224x224: torch.autocast(fp16) around the forward
• dinov2-vitl14 original 224x224: torch.autocast(fp16) around the forward
• dinov2-vitl14-reg original (fp32) 224x224, original 224x224: dinov2 forward_features CLS
• dinov2-vitg14 original 224x224: torch.autocast(fp16) around the forward
• dinov2-vitg14-reg original (fp32) 224x224, original 224x224: dinov2 forward_features CLS
• dinov2-vits14 load / first call: original 0.41 s / 0.174 s, portable 0.07 s / 0.118 s, kernels 0.07 s / 0.153 s
• dinov2-vits14-reg load / first call: original 1.32 s / 0.107 s, portable 0.21 s / 0.126 s, kernels 0.08 s / 0.167 s
• dinov2-vitb14 load / first call: original 1.51 s / 0.006 s, portable 0.27 s / 0.205 s, kernels 0.19 s / 0.191 s
• dinov2-vitb14-reg load / first call: original 1.71 s / 0.035 s, portable 0.59 s / 0.042 s, kernels 0.21 s / 0.205 s
• dinov2-vitl14 load / first call: original 7.06 s / 0.013 s, portable 0.57 s / 0.148 s, kernels 0.57 s / 0.179 s
• dinov2-vitl14-reg load / first call: original 4.6 s / 0.068 s, portable 0.66 s / 0.113 s, kernels 0.56 s / 0.205 s
• dinov2-vitg14 load / first call: original 19.29 s / 0.046 s, portable 4.37 s / 0.104 s, kernels 2.22 s / 0.162 s
• dinov2-vitg14-reg load / first call: original 14.67 s / 0.089 s, portable 4.32 s / 0.033 s, kernels 2.91† s / 0.017 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, dinov2-vits14, dinov2-vits14-reg, dinov2-vitb14, dinov2-vitb14-reg, dinov2-vitl14, dinov2-vitl14-reg, dinov2-vitg14: first call, 3 warm-up, peak reset, median of 3 rounds x median of 5
• Protocol, dinov2-vitg14-reg: median of 5 after 3 warm-up, uint8 CUDA input (synthetic for bench_inputs sizes), card defaults; gc before each load; peak = max over the first call and the timed calls

Measured

Two disjoint seeded subsets of the val folders; each image shorter side 256 (bicubic), centre crop 224, the CLS / pooled feature; cosine kNN, vote weighted by similarity. 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| <= 0.0001 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 2.5 % and p99 <= 12 % of the reference's median |value| (absolute error of the output last_hidden_state).