{"library":"torchao","type":"library","category":null,"description":"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.","language":"python","status":"active","version":"0.17.0","tags":["pytorch","quantization","optimization","deep-learning","gpu","low-precision"],"last_verified":"Wed May 20","install":[{"cmd":"pip install torchao","imports":["from torchao.quantization import quantize_","from torchao.quantization.quant_config import QuantConfig","from torchao.quantization import int8_dynamic_activation_int4_weight","from torchao.sparsity import apply_sparse_weights"]}],"homepage":null,"github":"https://github.com/pytorch/ao","docs":null,"changelog":null,"pypi":"https://pypi.org/project/torchao/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":50,"avg_install_s":2.2,"avg_import_s":null,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/torchao/compatibility"}}