NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
☆12,800Mar 9, 2026Updated last week
Alternatives and similar repositories for TensorRT
Users that are interested in TensorRT are comparing it to the libraries listed below
Sorting:
- ONNX-TensorRT: TensorRT backend for ONNX☆3,194Feb 3, 2026Updated last month
- An easy to use PyTorch to TensorRT converter☆4,858Aug 17, 2024Updated last year
- Implementation of popular deep learning networks with TensorRT network definition API☆7,720Mar 7, 2026Updated last week
- PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT☆2,958Updated this week
- The Triton Inference Server provides an optimized cloud and edge inferencing solution.☆10,426Updated this week
- TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizat…☆13,120Updated this week
- Transformer related optimization, including BERT, GPT☆6,397Mar 27, 2024Updated last year
- Open standard for machine learning interoperability☆20,484Updated this week
- Simplify your onnx model☆4,309Feb 26, 2026Updated 3 weeks ago
- Open Machine Learning Compiler Framework☆13,197Updated this week
- ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator☆19,568Updated this week
- Development repository for the Triton language and compiler☆18,656Updated this week
- ncnn is a high-performance neural network inference framework optimized for the mobile platform☆22,908Updated this week
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆9,442Updated this week
- Visualizer for neural network, deep learning and machine learning models☆32,592Updated this week
- A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep lear…☆5,642Updated this week
- A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch☆8,931Mar 10, 2026Updated last week
- Fast and memory-efficient exact attention☆22,832Updated this week
- Simple samples for TensorRT programming☆1,656Mar 2, 2026Updated 2 weeks ago
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.☆41,807Updated this week
- OpenMMLab Detection Toolbox and Benchmark☆32,507Aug 21, 2024Updated last year
- MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.☆14,533Updated this week
- Ongoing research training transformer models at scale☆15,647Updated this week
- State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enter…☆14,745Aug 12, 2024Updated last year
- Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.☆8,755Oct 16, 2025Updated 5 months ago
- A primitive library for neural network☆1,367Nov 24, 2024Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMs☆73,479Updated this week
- Tensors and Dynamic neural networks in Python with strong GPU acceleration☆98,243Updated this week
- CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.☆2,661Jan 22, 2026Updated last month
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,211Updated this week
- Object detection, 3D detection, and pose estimation using center point detection:☆7,546Mar 2, 2023Updated 3 years ago
- Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.☆34,223Updated this week
- Samples for CUDA Developers which demonstrates features in CUDA Toolkit☆8,953Jan 6, 2026Updated 2 months ago
- OpenVINO™ is an open source toolkit for optimizing and deploying AI inference☆9,880Updated this week
- Deploy your model with TensorRT quickly.☆764Nov 21, 2023Updated 2 years ago
- YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documenta…☆10,376Jun 8, 2025Updated 9 months ago
- TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is …☆4,626May 9, 2025Updated 10 months ago
- The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights --…☆36,504Updated this week
- Optimized primitives for collective multi-GPU communication☆4,531Updated this week