CVCUDA / CV-CUDA
CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.
☆2,381Updated last month
Related projects ⓘ
Alternatives and complementary repositories for CV-CUDA
- Simple samples for TensorRT programming☆1,519Updated 2 weeks ago
- PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT☆2,597Updated this week
- Simplify your onnx model☆3,865Updated 2 months ago
- ONNX-TensorRT: TensorRT backend for ONNX☆2,953Updated 2 weeks ago
- OpenMMLab Model Deployment Framework☆2,777Updated last month
- A tool to modify ONNX models in a visualization fashion, based on Netron and Flask.☆1,346Updated 2 weeks ago
- Set of Python bindings to C++ libraries which provides full HW acceleration for video decoding, encoding and GPU-accelerated color space …☆1,315Updated 5 months ago
- OpenMMLab Foundational Library for Training Deep Learning Models☆1,178Updated 2 weeks ago
- PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.☆1,558Updated 7 months ago
- ppl.cv is a high-performance image processing library of openPPL supporting various platforms.☆493Updated 3 weeks ago
- Actively maintained ONNX Optimizer☆647Updated 8 months ago
- NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source compone…☆10,820Updated 2 weeks ago
- CUDA Library Samples☆1,617Updated this week
- Deploy your model with TensorRT quickly.☆762Updated 11 months ago
- An easy to use PyTorch to TensorRT converter☆4,612Updated 3 months ago
- SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX R…☆2,227Updated this week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs…☆1,979Updated this week
- Sample codes for my CUDA programming book☆1,572Updated last year
- Examples for using ONNX Runtime for machine learning inferencing.☆1,212Updated 2 weeks ago
- nndeploy是一款模型端到端部署框架。以多端推理以及基于有向无环图模型部署为基础，致力为用户提供跨平台、简单易用、高性能的模型部署体验。☆633Updated this week
- AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (N…☆4,561Updated 3 weeks ago
- A primitive library for neural network☆1,295Updated 2 weeks ago
- ☆990Updated 8 months ago
- 🛠 A lite C++ toolkit of 100+ awesome AI models, support ONNXRuntime, MNN, TNN, NCNN and TensorRT.☆3,661Updated 3 weeks ago
- Several simple examples for popular neural network toolkits calling custom CUDA operators.☆1,339Updated 3 years ago
- ☆2,205Updated 10 months ago
- Implementation of popular deep learning networks with TensorRT network definition API☆7,016Updated 3 weeks ago
- TensorRT C++ API Tutorial☆626Updated this week
- yolort is a runtime stack for yolov5 on specialized accelerators such as tensorrt, libtorch, onnxruntime, tvm and ncnn.☆721Updated this week
- 🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥☆3,124Updated last year