July 10, 2026
- Improve optimizer
torch.compileand tensor learning-rate support. - Extend NaFlexViT patch-layout (for NaFlex-CLAP), and
forward_intermediates(NaFlex dict input) support. - Harden pickle loading and improve custom-label inference.
- Release 1.0.28
May 27, 2026
- Add model defs and pretrained weights for EUPE ViT (DINOv3-style) and ConvNeXt models. See the Efficient Universal Perception Encoder paper.
- Add TIPSv2 model defs and pretrained weights for (DINOv2-style) ViTs. See the TIPSv2 paper.
What's Changed
- validate.py: add --seed for reproducible validation by @janbernloehr in #2702
- Add tipsv2 vision encoders by @rwightman in #2705
- Initial EUPE model defs, slight tweaks for weight conversion. by @rwightman in #2706
- Support better torch.compile use by using torch.tensor for step count by @rwightman in #2704
- Preliminary naflexvit support for genlip image encoder (gated attn + mrope)) by @rwightman in #2707
- Address a few pickle security concerns. by @rwightman in #2708
- Fix ZeroDivisionError in AverageMeter.update when count is 0 by @CharlesCNorton in #2709
- Adding patchify_channels_last flag to unify support across data pipeline & naflex cfg/model by @rwightman in #2710
- Fix reg_token not being added to no-weight decay and stem/embed lr group by @rwightman in #2713
- Make doc builds faster by @mishig25 in #2714
- Fix inference.py labels for models fine-tuned on non-ImageNet datasets by @javierdejesusda in #2715
- Support NaFlex dict inputs for forward_intermediates by @rwightman in #2716
- Fixes for 1.0.28 release by @rwightman in #2717
New Contributors
- @janbernloehr made their first contribution in #2702
- @CharlesCNorton made their first contribution in #2709
- @javierdejesusda made their first contribution in #2715
Full Changelog: v1.0.27...v1.0.28