optimum
https://github.com/huggingface/optimum
Python
๐ Accelerate training and inference of ๐ค Transformers and ๐ค Diffusers with easy to use hardware optimization tools
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported2 Subscribers
Add a CodeTriage badge to optimum
Help out
- Issues
- Add BetterTransformer support for SEW
- Inference stuck๏ผ
- [TFLite Export] Adds TFLite support for LayoutLMv3
- ONNX weight deduplication is slow for large models
- Add ControlNet ONNX export
- Pruning feature
- Quantizer Not Respecting use_external_data_format
- Dissociate PyTorch / ONNX Runtime benchmark scripts
- Add option to save benchmark results
- [optimum-onnxruntime] The number of calibration samples must be divisible by (num_calibration_shards * calibration_batch_size)
- Docs
- Python not yet supported