/neural-compressor

Provide unified APIs for SOTA model compression techniques, such as low precision (INT8/INT4/FP4/NF4) quantization, sparsity, pruning, and knowledge distillation on mainstream AI frameworks such as TensorFlow, PyTorch, and ONNX Runtime.

Primary LanguagePythonApache License 2.0Apache-2.0

Watchers

No one’s watching this repository yet.