PyTorch AO (torchao)

TorchAO is a PyTorch library for applying advanced optimization (AO) techniques, primarily quantization and sparsity, to deep learning models running on GPUs. It focuses on performance acceleration through low-precision kernels, mixture-of-experts (MoE) optimizations, and quantization-aware training (QAT). The current version is 0.17.0, with new versions and significant features released frequently, often monthly.