Byted PyTorch Distributed for Hyperscale Training of LLMs and RLs

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

Build compute kernels and load them from the Hub.

A lightweight, AI-native training framework for large language models. Designed for fast iteration, reproducible experiments, and modular configuration across SFT, RLVR, and evaluation workflows.

Kernel sources for https://huggingface.co/kernels-ext-npu

AgentHub SDK is the unified and transparent multi-LLM SDK for building reliable Agent Apps. (GPT-5.5/Claude 4.8/Gemini 3.5)

A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.

Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation

📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

A collection of memory efficient attention operators implemented in the Triton language.

USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference

🚀 Efficient implementations for emerging model architectures

Nano vLLM

Democratizing Reinforcement Learning for LLMs

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

General-purpose AI designed for knowledge workers — creators, strategists, and operators — and individuals seeking AI systems they can truly control to help them get work done, with full flexibilit…

Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: …

Financial data platform for analysts, quants and AI agents.

The agent engineering platform.

A flexible and efficient training framework for large-scale alignment tasks

A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators.

Puzzles for learning Triton, play it with minimal environment configuration!

Cataloging released Triton kernels.

A lightweight data processing framework built on DuckDB and 3FS.

A high-performance distributed file system designed to address the challenges of AI training and inference workloads.

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

Legado 3.0 Book Reader with powerful controls & full functions❤️阅读3.0, 阅读是一款可以自定义来源阅读网络内容的工具，为广大网络文学爱好者提供一种方便、快捷舒适的试读体验。