A local-first routing and coordination engine for long-running agent work.

Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU sharding,…

GPT-2-style LLM built from scratch in C/CUDA with hand-written backprop, BPE tokenizer, FlashAttention, pretraining, and SFT.

Generate text, images, video, speech, and music by MiniMax.

Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.

Agent skill that removes signs of AI-generated writing from text

《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码

vLLM plugin for attention-ffn disaggregation support

《深入理解 AI Infra：量化分析与系统设计》（李博杰 著）开源书稿：从硬件约束和模型架构出发，量化推导 LLM 推理与训练系统设计。含全书正文、PDF、配套计算工具与实验

An agent harness that compiles a model into one provably-correct, self-retargeting CUDA megakernel and self-tunes it past cuBLAS at batch-1 LLM decode, paper: https://arxiv.org/abs/2606.09682

A transparent, in-container GPU resource controller that enforces memory and compute limits by intercepting CUDA calls without application or driver changes.

SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models.

Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.

CUDA Library Samples

Optimized primitives for collective multi-GPU communication

Ecosystem of libraries and tools for writing and executing fast GPU code fully in Rust.

A modern replacement for Redis and Memcached

Nephio is a Kubernetes-based automation platform for deploying and managing highly distributed, interconnected workloads such as 5G Network Functions, and the underlying infrastructure on which tho…

LLM inference in C/C++

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Go bindings to systemd socket activation, journal, D-Bus, and unit files

Kubernetes controllers for fast model actuation using vLLM sleep/wake and launcher-based model swapping

Make Every Team AI Native

学摩尔线程 MUSA SDK 的学习记录

how to optimize some algorithm in cuda.