Enable fp16 on CPU (#30459)

Commit

1 year ago

Enable fp16 on CPU (#30459) * Check removing flag for torch * LLM oops * Getting there... * More discoveries * Change * Clean up and prettify * Logic check * Not

References

#29969 - [SigLIP] Add fast tokenizer

#30459 - Enable fp16 on CPU

#32831 - [Docs] Update resources

#33111 - [Backbone] Remove out_features everywhere

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

#39821 - Support MetaCLIP 2

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

#41212 - Add EoMT with DINOv3 backbone

#62 - Add initial DEIMv2 model implementation

Author

muellerzr

Parents

d1d94d79

transformers 5c57463b - Enable fp16 on CPU (#30459)

transformers
5c57463b - Enable fp16 on CPU (#30459)