Starred repositories
Context engineering is the new vibe coding - it's the way to actually make AI coding assistants work. Claude Code is the best for this so that's what this repo is centered around, but you can apply…
Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM
Community maintained hardware plugin for vLLM on Ascend
A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.
坚持分享 GitHub 上高质量、有趣实用的开源技术教程、开发者工具、编程网站、技术资讯。A list cool, interesting projects of GitHub.
大模型算法岗面试题(含答案):常见问题和概念解析 "大模型面试题"、"算法岗面试"、"面试常见问题"、"大模型算法面试"、"大模型应用基础"
FlashMLA: Efficient Multi-head Latent Attention Kernels
This is the official repository for The Hundred-Page Language Models Book by Andriy Burkov
Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
动手学数据分析以项目为主线，知识点孕育其中，通过边学、边做、边引导来得到更好的学习效果
The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.
《机器学习理论导引》（宝箱书）的证明、案例、概念补充与参考文献讲解。
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理
A curated list of Large Language Model resources, covering model training, serving, fine-tuning, and building LLM applications.
The LLM's practical guide: From the fundamentals to deploying advanced LLM and RAG apps to AWS using LLMOps best practices
Kubernetes Handbook （Kubernetes指南） https://kubernetes.feisky.xyz
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉
Free and Open Source, Distributed, RESTful Search Engine
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance…
Simple, safe way to store and distribute tensors
Robust recipes to align language models with human and AI preferences
《大模型白盒子构建指南》：一个全手搓的Tiny-Universe