Starred repositories
A self-hosted ML coding practice platform. 68 problems from ReLU to flow matching — attention, training, RLHF, diffusion, and more. Instant feedback in the browser.
how to optimize some algorithm in cuda.
My learning notes for ML SYS.
SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models.
Secure environments for developers and their agents
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
Flash Attention in ~100 lines of CUDA (forward pass only)
Codes & examples for "CUDA - From Correctness to Performance"
If you live in the terminal, kitty is made for you! Cross-platform, fast, feature-rich, GPU based.
Bilingual tutorial for building coding agents, distilled from Pi Agent architecture.
Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation
nano-vllm 面试导向学习指南 | 20节课程 + 72道面试八股文 + STAR面试法 + 哆啦A梦风格漫画
Optimized primitives for collective multi-GPU communication
A framework for efficient model inference with omni-modality models
A lightweight library for xPU kernel JIT compilation
Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (N…
🎓从0开始训练一个大模型Minimind项目的超详细解析，包括但不限于用到的架构，算法，以及大模型面试经验
仅需Python基础，从0构建自己的具身智能机器人；从0逐步构建VLA/OpenVLA/SmolVLA/Pi0， 深入理解具身智能
面向开发者与初学者的 nano-vLLM 交互式源码教程 - 通过 13 个 HTML 互动实验 + 13 章中文教程理解大模型推理引擎
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
Open Multi-Agent Interactive Classroom — Get an immersive, multi-agent learning experience in just one click
Official SGLang x Datawhale course on LLM inference: understand inference, build a mini-sglang from scratch, then read the real SGLang source and land your first PR. Available in English and Chinese.
An AI creative platform for novel writing and AI generated RPG, with built-in support for AI agents, Skills, subagent workflows, automations, image generation, and version control.