# HuangOwen/Awesome-LLM-Compression

Awesome LLM compression research papers and tools.

Repository: https://github.com/HuangOwen/Awesome-LLM-Compression
Canonical: https://ross.abutalabs.com/products/awesome-llm-compression
License: MIT
License Family: permissive
Last push: 2026-08-26T20:30:44+00:00

## Health v2 (maintenance only)
Score: 74/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 85
- inputs: {"age_days": 1191, "days_push": 7, "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 1865, forks 130 (observed 2026-08-28T04:05:46.185188+00:00)

## What it is
A curated awesome-list of research papers and tools on large language model compression, covering quantization, pruning and sparsity, distillation, efficient prompting, and KV cache compression. Papers are organized by category and year, with a tools section for accelerating LLM training and inference.

## Use cases
- find recent papers on LLM quantization
- research KV cache compression techniques
- learn about pruning and sparsity for large language models
- discover knowledge distillation methods for LLMs
- find tools to compress and accelerate LLM inference
- survey efficient prompting techniques
- keep up with LLM efficiency research by year

## When to choose
- you need a curated, categorized reading list on LLM compression
- you want to track the latest efficiency papers grouped by year
- you are looking for both papers and practical compression tools in one place

## When to avoid
- you need runnable compression software rather than a paper index
- you want tutorials or courses rather than research paper links
- you need compression methods for non-LLM models

## Facets
- artifact type: learning-resource
- maturity: active
- function: llm-inference, llm-training, machine-learning
- domain: large-language-models, machine-learning, artificial-intelligence, awesome-lists, tutorials
- platform: -
- tags: awesome-list, model-compression, quantization, pruning, knowledge-distillation, kv-cache, research-papers, efficiency, web-server

## Member repositories
- HuangOwen/Awesome-LLM-Compression (main) score 74

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:46.185188+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 2026-08-30T03:15:33.138922+00:00, confidence not recorded.
  - readme: https://github.com/HuangOwen/Awesome-LLM-Compression (fetched 2026-08-28T04:05:46.185188+00:00, sha f03c63d71f62)
- Data as of 2026-08-30T08:39:29.467469+00:00.