External-model router for Codex with guided Kimi OAuth/API, DeepSeek, safe migration, and rollback.

AI that sees your screen, listens to your conversations and tells you what to do

CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs

Ulysses sequence-parallel all-to-all as a torch custom op, moved by the GPU copy engines into torch symmetric memory. Zero SM usage; 1.66-2.17x over torch.distributed on NVLink.

分享AI Infra知识&代码练习：PyTorch、vLLM/SGLang、slime/vime框架入门⚡️、性能加速🚀、大模型基础🧠、AI软硬件🔧等

let coding agents use ncu skills analysis cuda program automatically!

⛰️ The Life Operating System — an intent engineering platform that moves you from your current state to your ideal state, in life and work.

Mixture-of-experts (MoE) training megakernel for NVL72s

tiny vision language model

🪄 Flint is a visualization language that lets AI agents reliably create expressive, good-looking charts from simple, human-editable chart specs.

A host-based framework that transparently extends the GPU addressable global memory space beyond the host memory using NVM-backed data pointers

🍎 One kernel a day keeps high latency away. A hands-on CUDA learning path featuring a rich collection of kernels, from the basics to peak performance, seamlessly integrated as PyTorch C++ extensions.

Reference implementation and examples of the CuTe Layout representation and algebra.

Inference Llama 2 in one file of pure C

PyTorch library for cost-effective, fast and easy serving of MoE models.

MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts

Agentic Kernel Optimization for All — automated GPU kernel optimization for any kernel, any hardware, any language

Kernels, of the mega variety :)

A high-throughput and memory-efficient inference and serving engine for LLMs

SGLang with X-Mem support for KV offloading

Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local

Nsight Python is a Python kernel profiling interface based on NVIDIA Nsight Tools

SGLang kernel library for NPU

DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms

Understanding R1-Zero-Like Training: A Critical Perspective

Codex Autoresearch Skill — A self-directed iterative system for Codex that continuously cycles through: modify, verify, retain or discard, and repeat indefinitely. Inspired by Karpathy’s autoresear…