{"library":"executorch","type":"library","category":null,"description":"ExecuTorch is an on-device AI framework that extends PyTorch to mobile, embedded, and edge devices. It enables efficient inference by compiling PyTorch models into a compact, optimized format (.pte file) suitable for resource-constrained environments. The current version, 1.2.0, expands model and hardware support, including real-time speech and improved embedded targets. Releases are frequent, typically every 1-2 months, aligning with PyTorch releases.","language":"python","status":"active","version":"1.2.0","tags":["pytorch","on-device-ai","edge-ai","embedded","machine-learning","inference","mobile-ai"],"last_verified":"Tue May 26","install":[{"cmd":"pip install executorch","imports":["from torch._export.executorch import to_executorch","from torch.export import export","from executorch.backends.xnnpack.partition.xnnpack_partitioner import XnnpackPartitioner"]},{"cmd":"pip install executorch[xnnpack] # Or [coreml], [qnn], etc.","imports":[]}],"homepage":"https://pytorch.org/executorch/","github":"https://github.com/pytorch/executorch","docs":null,"changelog":"https://github.com/pytorch/executorch/releases","pypi":"https://pypi.org/project/executorch/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":35,"avg_install_s":102.3,"avg_import_s":null,"wheel_type":"sdist"},"url":"https://checklist.day/v1/registry/executorch/compatibility"}}