# HuaizhengZhang/AI-Infra-from-Zero-to-Hero

🚀 Awesome System for Machine Learning ⚡️ AI System Papers and Industry Practice. ⚡️ System for Machine Learning, LLM (Large Language Model), GenAI (Generative AI). 🍻 OSDI, NSDI, SIGCOMM, SoCC, MLSys, etc. 🗃️ Llama3, Mistral, etc. 🧑‍💻 Video Tutorials.

Repository: https://github.com/HuaizhengZhang/AI-Infra-from-Zero-to-Hero
Canonical: https://ross.abutalabs.com/products/ai-infra-from-zero-to-hero
Homepage: https://huaizheng.xyz/
License: MIT
License Family: permissive
Topics: large-language-models, ai-infra, genai, mlsys, model-serving, model-training, llmsys
Last push: 2025-07-25T02:24:35+00:00

## Health v2 (maintenance only)
Score: 47/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 33, release rhythm 35, longevity 100
- inputs: {"age_days": 2795, "days_push": 405, "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 4309, forks 410 (observed 2026-08-28T04:08:41.738004+00:00)

## What it is
A curated awesome-list of research papers, industry practices, and video tutorials on systems for machine learning, LLMs, and generative AI. It organizes resources by ML/DL infrastructure, LLM training and serving, and domain-specific systems, tied to top systems conferences like OSDI, NSDI, and MLSys.

## Use cases
- learn AI infrastructure from research papers
- find papers on LLM training and serving systems
- study MLSys and OSDI conference papers on ML systems
- get video tutorials explaining vLLM and LLM serving internals
- find resources on machine learning systems engineering
- prepare for research in AI systems and infrastructure

## When to choose
- you want a curated, categorized reading list of ML/LLM systems research
- you prefer learning via video walkthroughs of real systems like vLLM
- you need pointers to code implementations alongside papers
- you are a student or researcher entering the MLSys field

## When to avoid
- you need runnable software or a production tool rather than a reading list
- you want beginner tutorials on using ML frameworks rather than systems research
- you need up-to-date product documentation for a specific serving framework

## Facets
- artifact type: learning-resource
- maturity: active
- function: llm-inference, llm-training, machine-learning, deep-learning, gpu-computing
- domain: machine-learning, deep-learning, large-language-models, gpu-computing, tutorials, awesome-lists
- platform: cross-platform
- tags: awesome-list, mlsys, ai-infrastructure, model-serving, research-papers, video-tutorials

## Member repositories
- HuaizhengZhang/AI-Infra-from-Zero-to-Hero (main) score 47

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:41.738004+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 2026-08-29T18:21:47.786132+00:00, confidence not recorded.
  - readme: https://github.com/HuaizhengZhang/AI-Infra-from-Zero-to-Hero (fetched 2026-08-28T04:08:41.738004+00:00, sha 0812e5fb497e)
  - homepage: https://huaizheng.xyz/ (fetched 2026-08-29T09:11:11.624789+00:00, sha dd3c8fc3b13a)
- Data as of 2026-08-30T08:39:29.467469+00:00.