cuda

🚀🚀🚀A collection of some awesome public projects about Large Language Model(LLM), Vision Language Model(VLM), Vision Language Action(VLA), AI Generated Content(AIGC), the related Datasets and Applications.

TIGRE: Tomographic Iterative GPU-based Reconstruction Toolbox

[内测中]QPT - 致力于让开源项目更好通往互联网世界的Python to EXE工具（Python打包）。

Fast Multi-dimensional Sparse Attention

High-performance GPU-accelerated signal processing and visualization framework that runs anywhere.

SOMA: Unifying Parametric Human Body Models

oneAPI Math Library (oneMath)

row-major matmul optimization

Official SGLang × Datawhale course on LLM inference (中英双语): understand inference, build a mini-sglang from scratch, then read the real SGLang source and land your first PR. 《从零手搓SGLang》：读懂推理，手搓 mini-sglang，吃透 SGLang 源码。

eBPF based always-on CPU/GPU profiler auto-discovering targets in Kubernetes and systemd, zero code changes or restarts needed!

Fast CUDA implementation of (differentiable) soft dynamic time warping for PyTorch

NVIDIA RMM is a library for allocating and managing GPU memory in C++ and Python.

VexCL is a C++ vector expression template library for OpenCL/CUDA/OpenMP

A fully local and private Speech-To-Text app, offering multiple model backends, diarization & calendar mode - Available for Windows, macOS & Linux

Vulkan, OptiX and CUDA Interoperation Modular Rendering Library and Framework for PC/Linux/Android

ThunderGBM: Fast GBDTs and Random Forests on GPUs

Serverless LLM Serving for Everyone.

A zero-dependency ML framework in C with a modern Python API for full control over execution and memory.

🎯 AI Zero to Hero 👑

Aim-bot based on AI for all FPS and TPS games

Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

Pure Rust Inference Engine

Local, OpenAI-compatible text-to-speech (TTS) API using Chatterbox, enabling users to generate voice cloned speech anywhere the OpenAI API is used (e.g. Open WebUI, AnythingLLM, etc.)

a reimplementation of PWC-Net in PyTorch that matches the official Caffe version

Real-time 3D full-body reconstruction from a single camera, Multiperson BVH output, Pure C++ runtime, ONNX + ggml, 70-joint skeleton with hands.

CUDA Voxelizer to convert polygon meshes into annotated voxel grids

Differentiable Fluid Dynamics Package

Our first fully AI generated deep learning system

A code generator for array-based code on CPUs and GPUs