A high performance deep learning inference library
Project Links
Meta
Author: NVIDIA Corporation
Requires Python: >=3.8
Classifiers
License
- Other/Proprietary License
Intended Audience
- Developers
Programming Language
- Python :: 3
NVIDIA TensorRT is an SDK that facilitates high-performance machine learning inference. It is designed to work in a complementary fashion with training frameworks such as PyTorch. It focuses specifically on running an already-trained network quickly and efficiently on NVIDIA hardware.
11.2.1.2
Jul 30, 2026
11.1.0.106
Jun 16, 2026
11.0.0.114
May 27, 2026
10.16.1.11
Apr 07, 2026
10.16.0.72
Mar 18, 2026
10.15.1.29
Jan 30, 2026
10.14.1.48.post1
Nov 07, 2025
10.14.1.48
Nov 04, 2025
10.13.3.9.post1
Nov 07, 2025
10.13.3.9
Sep 05, 2025
10.13.2.6
Aug 05, 2025
0.0.0a0
Apr 09, 2025
