AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

Fast and memory-efficient exact attention

A PyTorch implementation of the Transformer model in "Attention is All You Need".

🌱Light and powerful C++ web framework for highly scalable and resource-efficient web application. It's zero-dependency and easy-portable.

CUDA Templates for Linear Algebra Subroutines

check python dataloading speed

InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

TensorRT+YOLO系列的 多路 多卡 多实例 并行视频分析处理案例

A cross-platform video structuring (video analysis) framework. If you find it helpful, please give it a star: ) 跨平台的视频结构化（视频分析）框架，觉得有帮助的请给个星星 : )

An onnx-based quantitation tool.

Yolov5 inference on NVDec hardware decoder

Using pattern matcher in onnx model to match and replace subgraphs.

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

YOLOv5 on Orin DLA

XGBoost + Optuna

async inference for machine learning model

TensorRT Extension for Stable Diffusion Web UI

Kalman Filter book using Jupyter Notebook. Focuses on building intuition and experience, not formal proofs. Includes Kalman filters,extended Kalman filters, unscented Kalman filters, particle filte…

A project demonstrating Lidar related AI solutions, including three GPU accelerated Lidar/camera DL networks (PointPillars, CenterPoint, BEVFusion) and the related libs (cuPCL, 3D SparseConvolution…

A Library for Advanced Deep Time Series Models.

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…

高效部署：YOLO X, V3, V4, V5, V6, V7, V8, EdgeYOLO TRT推理 ™️ 🔝 ,前后处理均由CUDA核函数实现 CPP/CUDA🚀

C++ library based on tensorrt integration