NVIDIA/TensorRT
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
NVIDIA TensorRT is a toolkit for developers who need to optimize and deploy deep learning models on NVIDIA GPUs for faster performance. It takes trained AI models, typically from frameworks like TensorFlow or ONNX, and processes them to run much more efficiently. This helps bring AI applications to users with minimal delay, making things like real-time image analysis or recommendation systems more responsive.
12,784 stars. Used by 2 other packages. Actively maintained with 1 commit in the last 30 days. Available on PyPI.
Use this if you are a deep learning engineer or MLOps specialist looking to significantly speed up the inference performance of your AI models on NVIDIA hardware.
Not ideal if you are an end-user without deep learning development experience or if you need to train models, as TensorRT focuses solely on optimizing already-trained models for deployment.
Stars
12,784
Forks
2,321
Language
C++
License
Apache-2.0
Category
Last pushed
Mar 09, 2026
Commits (30d)
1
Dependencies
1
Reverse dependents
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/NVIDIA/TensorRT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Recent Releases
Compare
Related frameworks
microsoft/onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
onnx/onnx
Open standard for machine learning interoperability
PINTO0309/onnx2tf
Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The...
onnx/onnxmltools
ONNXMLTools enables conversion of models to ONNX
microsoft/onnxconverter-common
Common utilities for ONNX converters