Metadata-Version: 2.1
Name: tensorrt_rtx_cu13
Version: 1.4.0.76
Summary: A high performance deep learning inference library
Author: NVIDIA Corporation
License: Proprietary
Project-URL: Homepage, https://github.com/nvidia/tensorrt
Project-URL: Download, https://developer.nvidia.com/tensorrt
Keywords: nvidia,tensorrt,deeplearning,inference
Classifier: License :: Other/Proprietary License
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE.txt
Requires-Dist: tensorrt_rtx_cu13_libs==1.4.0.76
Requires-Dist: tensorrt_rtx_cu13_bindings==1.4.0.76
Provides-Extra: numpy
Requires-Dist: numpy; extra == "numpy"

NVIDIA TensorRT RTX is an SDK for high-performance AI inference on NVIDIA RTX GPUs. It includes a Just-in-Time compiler for fast on-device inference optimizations that enable portable deployments and runtime performance specialization. It also introduces convenience features such as built-in CUDA graph support, runtime cache, and a simplified development workflow.
