Highlights
- Pro
Lists (15)
Stars
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
Tesseract Open Source OCR Engine (main repository)
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
Productive, portable, and performant GPU programming in Python.
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
FlashMLA: Efficient Multi-head Latent Attention Kernels
CUDA Templates and Python DSLs for High-Performance Linear Algebra
Mesh optimization library that makes meshes smaller and faster to render
Transformer related optimization, including BERT, GPT
Lightning fast C++/CUDA neural network framework
CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.
Nvdiffrast - Modular Primitives for High-Performance Differentiable Rendering
Split screen video comparison tool using FFmpeg and SDL2
[CVPR 2024 Highlight] Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering
A library created to revitalize C++ as a machine learning front end. Per aspera ad astra.
The open source mesh processing python library
RaDe-GS: Rasterizing Depth in Gaussian Splatting
PlenOctree Volume Rendering (supports CUDA & fragment shader backends)
[CVPR 2024 Highlight] Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields
code for GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfaces
D-Map provides an efficient occupancy mapping approach for high-resolution LiDAR sensors.
Shape Aware Parallel Mesh Simplification Algorithm
A simple database engine with common SQL queries support. Final project for course 'Introduction to Databases' of Tsinghua University, Fall 2018.