August 27, 2026
- Add LowFormer model and weights
- Fix or merge a host of real but small or not commonly encountered bugs surfaced by agents
- Release 1.0.29
August 11, 2026
- Add model defs and pretrained weights for
- CPUBone, an efficient vision backbone for devices with low parallelization capabilities.
- PP-LCNetV2.
- LingBot-Vision.
- Add per-batch image and batch size scheduling for non-NaFlex training, including progressive small-to-large resolution schedules.
- Improve NaFlexViT with key-only attention masks, compile-friendly and memory-efficient position sampling, and cached variable-patch interpolation.
- Improve model factory path and checkpoint handling; fix equal-token positional embedding resampling.
What's Changed
- Add optional key-only masks for NaFlexVit self-attention by @chenghuichen in #2719
- Make NaFlex position embedding sampling compile-friendly and memory-efficient by @chenghuichen in #2720
- Variable train image sizes by @rwightman in #2722
- Improved model factory path handling. Fix #2725 by @rwightman in #2727
- Naflex interp cache by @rwightman in #2728
- Cpubone by @rwightman in #2733
- Fix positional embedding resampling for equal-token grid changes by @aswanth-07 in #2737
- Add LingBot-Vision models by @belfner in #2730
- Add PP-LCNetV2 (lcnetv2_small / lcnetv2_base / lcnetv2_large) by @developer0hye in #2736
- Fix CutMix minmax border sampling by @tandede in #2739
- A few more mixup / cutmix / bbox range fixups by @rwightman in #2740
- Return the fused RMSNorm2d result directly by @Robertboy18 in #2741
- Fix custom input channels for pruned EfficientNet models by @aswanth-07 in #2742
- Preserve classifier head device and dtype on reset by @aswanth-07 in #2743
- Fix load_pretrained helper in NaFlexVit, make purpose clear by @rwightman in #2746
- Fix AttributeError in auto-augment factories when hparams is None by @winklemad in #2747
- Fix AdafactorBigVision dropping the factored row normalization for tall matrices by @winklemad in #2749
- Fix auto-augment 'inc' and 'b' config flags ignoring the documented 0 value by @winklemad in #2748
- Fix SGDW foreach path applying weight decay once per (device, dtype) group by @winklemad in #2750
- Fix OptimizerRegistry.create_optimizer crash on layer_decay without an explicit min scale by @winklemad in #2754
- Fix device / dtype change for all classifier resets by @rwightman in #2752
- Add LowFormer by @brianhou0208 in #2755
New Contributors
- @chenghuichen made their first contribution in #2719
- @aswanth-07 made their first contribution in #2737
- @tandede made their first contribution in #2739
- @Robertboy18 made their first contribution in #2741
- @winklemad made their first contribution in #2747
Full Changelog: v1.0.28...v1.0.29