Optimum documentation
Overview
Overview
Nvidia
AMD
Intel
AWS Trainium/Inferentia
Google TPUs
for Intel Gaudi
ExecuTorch
Furiosa
ONNX Runtime
Exporters
BetterTransformer
Torch FX
LLM quantization
Utilities
Overview
🤗 Optimum enables exporting models from PyTorch or TensorFlow to different formats through its exporters module. For now, three exporting format are supported: ONNX and TFLite (TensorFlow Lite).