# liguodongiot/llm-action

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）

Repository: https://github.com/liguodongiot/llm-action
Canonical: https://ross.abutalabs.com/products/llm-action
Homepage: https://www.zhihu.com/column/c_1456193767213043713
Language: HTML
License: Apache-2.0
License Family: permissive
Topics: llm, llm-inference, llm-serving, llm-training, llmops
Last push: 2026-07-19T13:13:31+00:00

## Health v2 (maintenance only)
Score: 71/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 93, release rhythm 35, longevity 85
- inputs: {"age_days": 1198, "days_push": 45, "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 24958, forks 2846 (observed 2026-08-28T04:11:37.736189+00:00)

## What it is
A curated Chinese-language knowledge base covering large language model engineering, including training, fine-tuning, inference, compression, evaluation, and deployment. It aggregates tutorials, code examples, and deep dives into LLM infrastructure and application practices.

## Use cases
- learn how to fine-tune large language models with LoRA or QLoRA
- understand distributed training parallelism techniques for LLMs
- compare LLM inference frameworks and optimization methods
- learn LLM quantization, pruning, and knowledge distillation
- get started with RLHF and model alignment
- study LLM evaluation and inference performance benchmarking
- learn prompt engineering and LLM application development

## When to choose
- you want a comprehensive, structured reference on LLM engineering from training to serving
- you prefer Chinese-language tutorials with hands-on code examples
- you need guidance on distributed training and AI infrastructure

## When to avoid
- you need production-ready software rather than educational material
- you only want English-language documentation
- you seek a maintained library or tool to integrate into your codebase

## Facets
- artifact type: learning-resource
- maturity: active
- function: llm-training, llm-inference, rag, prompt-engineering, benchmarking
- domain: large-language-models, machine-learning, deep-learning, tutorials, gpu-computing
- platform: python, cloud
- tags: llmops, fine-tuning, lora, rlhf, quantization, distributed-training, inference-optimization, model-compression, chinese-language, gpu, linux

## Member repositories
- liguodongiot/llm-action (main) score 71

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:37.736189+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 2026-08-29T16:56:08.174066+00:00, confidence not recorded.
  - readme: https://github.com/liguodongiot/llm-action (fetched 2026-08-28T04:11:37.736189+00:00, sha 9ce588ca7568)
- Data as of 2026-08-30T08:39:29.467469+00:00.