transformers
99d67f1a - Improve greedy search memory usage (#32895)

Commit

1 year ago

Improve greedy search memory usage (#32895) Do not call torch.repeat_interleave if expand_size is 1

References

#29969 - [SigLIP] Add fast tokenizer

#32895 - Improve greedy search memory usage

#33111 - [Backbone] Remove out_features everywhere

#33174 - [Zero-shot image classification pipeline] Remove tokenizer_kwargs

#39821 - Support MetaCLIP 2

#58 - Add EoMT DINOv3 model

#59 - Fix attention mask handling in EoMT-DINOv3 converter

#41212 - Add EoMT with DINOv3 backbone

#62 - Add initial DEIMv2 model implementation

Author

regisss

regisss

Parents

Loading