AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。
☆8,523Dec 22, 2025Updated 10 months ago
Alternatives and similar repositories for AIInfra
Users that are interested in AIInfra are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术☆18,094Sep 3, 2025Updated last year
- An Open-source book with Modern CUDA learning Notes for Beginners - BF16/FP8/FP4, HGEMM, CuTe, Flash-Attention, etc.☆12,140Updated this week
- 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☆4,289Sep 20, 2026Updated last month
- Nano vLLM☆16,243Apr 26, 2026Updated 6 months ago
- My learning notes for ML SYS.☆7,624Oct 21, 2026Updated last week
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- AI Infra 全栈从0入门学习资料：https://caomaolufei.github.io/AIInfraGuide/☆3,053Updated this week
- CUDA 算子手撕与面试指南☆1,141Aug 23, 2025Updated last year
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,934Updated this week
- 本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型 应用落地）☆25,237Oct 14, 2026Updated 2 weeks ago
- how to optimize some algorithm in cuda.☆3,339Oct 11, 2026Updated 3 weeks ago
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆5,484May 17, 2026Updated 5 months ago
- FlashInfer: Kernel Library for LLM Serving☆6,821Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆38,321Updated this week
- AI 基础知识 - GPU 架构、CUDA 编程、大模型基础及AI Agent 相关知识。☆3,243Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- A high-throughput and memory-efficient inference and serving engine for LLMs☆95,977Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆8,865Updated this week
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆5,542Oct 20, 2026Updated last week
- 主要记录 大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题☆15,337Jun 14, 2026Updated 4 months ago
- 🚀 Awesome System for Machine Learning ⚡️ AI System Papers and Industry Practice. ⚡️ System for Machine Learning, LLM (Large Language Mod…☆4,454Jul 25, 2025Updated last year
- Material for gpu-mode lectures☆6,933Sep 9, 2026Updated last month
- hpc 教程，包含集合通信(mpi、nccl)、cuda 编程、向量化 SIMD、RDMA 通信等☆779Apr 27, 2026Updated 6 months ago
- This repository organizes materials, recordings, and schedules related to AI-infra learning meetings.☆613Mar 1, 2026Updated 7 months ago
- 🧠 Train a 64M-parameter LLM from scratch in just 2h!☆64,689Updated this week
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- 《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☆7,197Oct 1, 2026Updated last month
- Ongoing research training transformer models at scale☆18,305Updated this week
- 《Machine Learning Systems: Design and Implementation》 (V2 is launching soon）☆4,873Updated this week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆24,082Updated this week
- 校招、秋招、春招、实习好项目！带你从零实现一个高性能的深度学习推理库，支持大模型 llama2 、Unet、Yolov5、Resnet等模型的推理。Implement a high-performance deep learning inference library st…☆3,516Jun 22, 2025Updated last year
- 《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程☆32,656Updated this week
- Machine Learning Engineering Open Book☆19,637Updated this week
- Fast and memory-efficient exact attention☆25,233Updated this week
- 📚 从零开始构建大模型☆34,670Aug 8, 2026Updated 2 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- System for AI Education Resource.☆4,360Oct 25, 2024Updated 2 years ago
- A tutorial for CUDA&PyTorch☆532Mar 23, 2026Updated 7 months ago
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆10,681Updated this week
- Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation☆1,098Aug 29, 2026Updated 2 months ago
- compiler learning resources collect.☆2,789May 20, 2026Updated 5 months ago
- A self-learning tutorail for CUDA High Performance Programing.☆1,154Jan 14, 2026Updated 9 months ago
- ☆1,089Updated this week