{"library":"tensorrt","type":"library","category":null,"description":"NVIDIA TensorRT is a Python library and C++ SDK for high-performance deep learning inference. It optimizes trained neural networks for deployment on NVIDIA GPUs, focusing on throughput, latency, and memory efficiency. The current version is 10.16.1.11. NVIDIA typically releases minor updates to TensorRT frequently, often monthly or bi-monthly, with major versions released annually.","language":"python","status":"active","version":"10.16.1.11","tags":["deep-learning","inference","optimization","nvidia","gpu","cuda"],"last_verified":"Mon May 25","install":[{"cmd":"pip install tensorrt numpy cuda-python","imports":["import tensorrt as trt","from tensorrt import Logger","from cuda import cudart","trt.Builder","trt.NetworkDefinitionCreationFlag"]}],"homepage":"https://developer.nvidia.com/tensorrt","github":"https://github.com/nvidia/tensorrt","docs":null,"changelog":null,"pypi":"https://pypi.org/project/tensorrt/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":50,"avg_install_s":55.6,"avg_import_s":0.58,"wheel_type":"sdist"},"url":"https://checklist.day/v1/registry/tensorrt/compatibility"}}