mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-13 17:48:22 +06:00
78d78cdf8a
* Add TorchAOHfQuantizer Summary: Enable loading torchao quantized model in huggingface. Test Plan: local test Reviewers: Subscribers: Tasks: Tags: * Fix a few issues * style * Added tests and addressed some comments about dtype conversion * fix torch_dtype warning message * fix tests * style * TorchAOConfig -> TorchAoConfig * enable offload + fix memory with multi-gpu * update torchao version requirement to 0.4.0 * better comments * add torch.compile to torchao README, add perf number link --------- Co-authored-by: Marc Sun <marc@huggingface.co> |
||
|---|---|---|
| .. | ||
| agent.md | ||
| backbones.md | ||
| callback.md | ||
| configuration.md | ||
| data_collator.md | ||
| deepspeed.md | ||
| feature_extractor.md | ||
| image_processor.md | ||
| keras_callbacks.md | ||
| logging.md | ||
| model.md | ||
| onnx.md | ||
| optimizer_schedules.md | ||
| output.md | ||
| pipelines.md | ||
| processors.md | ||
| quantization.md | ||
| text_generation.md | ||
| tokenizer.md | ||
| trainer.md | ||