{"library":"torch-tensorrt","type":"library","category":null,"description":"Torch-TensorRT is a compiler for PyTorch/TorchScript models targeting NVIDIA TensorRT. Version 2.12.0 supports Python 3.10+. It automatically optimizes models for inference on NVIDIA GPUs. Release cadence roughly quarterly.","language":"python","status":"active","version":"2.12.0","tags":["tensorrt","nvidia","gpu","inference","compiler"],"last_verified":"Sun Jun 07","install":[{"cmd":"pip install torch-tensorrt","imports":["import torch_tensorrt","import torch"]},{"cmd":"conda install torch-tensorrt -c pytorch","imports":[]}],"homepage":"https://github.com/pytorch/tensorrt.git","github":"https://github.com/pytorch/tensorrt.git","docs":null,"changelog":null,"pypi":null,"npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":null}