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.
☆10,820Updated 2 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for TensorRT
- ONNX-TensorRT: TensorRT backend for ONNX☆2,953Updated 2 weeks ago
- PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT☆2,597Updated this week
- An easy to use PyTorch to TensorRT converter☆4,612Updated 3 months ago
- The Triton Inference Server provides an optimized cloud and edge inferencing solution.☆8,348Updated this week
- Simplify your onnx model☆3,865Updated 2 months ago
- Open deep learning compiler stack for cpu, gpu and specialized accelerators☆11,798Updated this week
- A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch☆8,415Updated 2 weeks ago
- Serve, optimize and scale PyTorch models in production☆4,218Updated 3 weeks ago
- ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator☆14,722Updated this week
- Open standard for machine learning interoperability☆17,949Updated this week
- Visualizer for neural network, deep learning and machine learning models☆28,167Updated this week
- Implementation of popular deep learning networks with TensorRT network definition API☆7,016Updated 3 weeks ago
- Development repository for the Triton language and compiler☆13,443Updated this week
- CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.☆2,381Updated last month
- OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference☆7,304Updated this week
- A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep lear…☆5,158Updated this week
- Transformer related optimization, including BERT, GPT☆5,890Updated 7 months ago
- State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enter…☆13,580Updated 3 months ago
- Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX☆2,327Updated 2 months ago
- Fast and memory-efficient exact attention☆14,279Updated this week
- AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.☆2,148Updated this week
- Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.☆30,559Updated this week
- PyTorch ,ONNX and TensorRT implementation of YOLOv4☆4,480Updated 5 months ago
- Tutorials for creating and using ONNX models☆3,386Updated 4 months ago
- PyTorch extensions for high performance and large scale training.☆3,195Updated last week
- oneAPI Deep Neural Network Library (oneDNN)☆3,635Updated this week
- NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone…☆5,771Updated 3 months ago
- Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125☆14,273Updated this week
- YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documenta…☆9,444Updated 3 months ago
- Google Brain AutoML☆6,251Updated 7 months ago