# AIoT-MLSys-Lab/Efficient-LLMs-Survey

[TMLR 2024] Efficient Large Language Models: A Survey

Repository: https://github.com/AIoT-MLSys-Lab/Efficient-LLMs-Survey
Canonical: https://ross.abutalabs.com/products/efficient-llms-survey
Homepage: https://arxiv.org/abs/2312.03863
License Family: other
Topics: generative-ai, large-language-models, machine-learning-systems, efficient-deep-learning, survey
Last push: 2025-06-23T01:57:02+00:00

## Health v2 (maintenance only)
Score: 42/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 28, release rhythm 35, longevity 88
- inputs: {"age_days": 1233, "days_push": 437, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1257, forks 100 (observed 2026-08-28T04:04:09.412003+00:00)

## What it is
A curated survey repository accompanying the TMLR 2024 paper 'Efficient Large Language Models: A Survey', organizing research on efficient LLMs into model-centric, data-centric, and framework-centric taxonomies. It is actively maintained with new papers added via pull requests.

## Use cases
- find papers on efficient LLM inference and training
- learn about LLM efficiency techniques like quantization and pruning
- get an overview of efficient deep learning research for large language models
- find a taxonomy of model-centric and data-centric LLM efficiency methods
- keep up with new research on efficient large language models
- find citations for a literature review on LLM efficiency

## When to choose
- you need a structured, peer-reviewed overview of efficient LLMs research
- you are starting research on LLM efficiency and want a reading list
- you want a maintained collection of papers on quantization, pruning, and efficient inference

## When to avoid
- you need runnable software or tools rather than a paper collection
- you need production-ready efficiency implementations
- you need a license permitting redistribution, since no license is specified

## Facets
- artifact type: learning-resource
- maturity: active
- function: documentation, developer-tools
- domain: large-language-models, machine-learning, artificial-intelligence, tutorials, awesome-lists
- platform: cross-platform
- tags: survey-paper, efficient-llms, model-compression, quantization, efficient-inference, efficient-training, tmlr, paper-collection

## Member repositories
- AIoT-MLSys-Lab/Efficient-LLMs-Survey (main) score 42

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:09.412003+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 2026-08-30T05:07:09.884754+00:00, confidence not recorded.
  - readme: https://github.com/AIoT-MLSys-Lab/Efficient-LLMs-Survey (fetched 2026-08-28T04:04:09.412003+00:00, sha ab04cc99f33d)
  - homepage: https://arxiv.org/abs/2312.03863 (fetched 2026-08-29T12:17:42.363901+00:00, sha b26b78bd6c61)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T12:17:42.373013+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T12:17:42.376419+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T12:17:42.378195+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T12:17:42.374842+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.