# Infrasys-AI/AIInfra

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。

Repository: https://github.com/Infrasys-AI/AIInfra
Canonical: https://ross.abutalabs.com/products/aiinfra
Homepage: https://infrasys-ai.github.io/aiinfra-docs/
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: aiinfra, aisystem
Last push: 2025-12-22T11:28:48+00:00

## Health v2 (maintenance only)
Score: 49/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 58, release rhythm 35, longevity 55
- inputs: {"age_days": 777, "days_push": 254, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 8029, forks 1037 (observed 2026-08-28T04:10:11.941399+00:00)

## What it is
AIInfra is an open-source Chinese-language course (text, slides, and videos) on AI infrastructure for large models, covering AI clusters, networking and storage, cloud-native tooling, distributed training and inference, and LLM algorithms and applications. It is the successor to the AISystem project, focused specifically on large-model systems.

## Use cases
- learn how large language model training and inference systems work
- understand AI cluster architecture and networking for LLM training
- study distributed training parallelism strategies for large models
- learn LLM inference optimization and model compression techniques
- understand Kubernetes and cloud-native deployment of AI workloads
- study Scaling Law and Transformer/MoE architecture fundamentals
- learn about AI agents and RAG system design

## When to choose
- you want a structured, in-depth curriculum on LLM system design from hardware to software
- you are a graduate student or engineer building or operating AI training/inference clusters
- you prefer Chinese-language materials with accompanying videos and slides
- you want free, regularly updated content with hands-on K8S and inference labs

## When to avoid
- you need production software or tooling rather than educational material
- you need beginner-level AI/ML tutorials without systems prerequisites
- you require English-only course materials
- you need a formal certification or accredited course

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, llm-training, llm-inference, gpu-computing, container-orchestration, developer-tools
- domain: large-language-models, deep-learning, gpu-computing, microservices, tutorials, cloud-computing
- platform: cloud, python
- tags: ai-infrastructure, open-course, distributed-training, llm-systems, chinese-language, slides, video-course, gpu, docker, kubernetes

## Member repositories
- Infrasys-AI/AIInfra (main) score 49

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:11.941399+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:31:48.127332+00:00, confidence not recorded.
  - readme: https://github.com/Infrasys-AI/AIInfra (fetched 2026-08-28T04:10:11.941399+00:00, sha 1d7e59bce709)
  - homepage: https://infrasys-ai.github.io/aiinfra-docs/ (fetched 2026-08-29T08:29:11.276396+00:00, sha 8d2094947c6c)
- Data as of 2026-08-30T08:39:29.467469+00:00.