# horseee/Awesome-Efficient-LLM

A curated list for Efficient Large Language Models

Repository: https://github.com/horseee/Awesome-Efficient-LLM
Canonical: https://ross.abutalabs.com/products/awesome-efficient-llm
Language: Python
License Family: other
Topics: compression, knowledge-distillation, language-model, llm, model-quantization, pruning-algorithms, efficient-llm, llm-compression
Last push: 2025-06-17T02:35:25+00:00

## Health v2 (maintenance only)
Score: 41/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 27, release rhythm 35, longevity 85
- inputs: {"age_days": 1199, "days_push": 443, "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 2036, forks 169 (observed 2026-08-28T04:06:08.041442+00:00)

## What it is
A curated awesome-list of research papers and resources on efficient large language models, covering pruning, quantization, knowledge distillation, KV cache compression, efficient MoE, and serving systems. It is organized into topic subdirectories with regularly updated recent papers and recommended reads.

## Use cases
- find papers on LLM quantization
- research KV cache compression techniques
- survey efficient fine-tuning methods
- learn about pruning and sparsity for transformers
- find inference acceleration research
- keep up with efficient MoE architectures
- find surveys and benchmarks on efficient LLMs

## When to choose
- starting research on efficient LLM techniques
- looking for a broad, organized survey of model compression literature
- tracking recent papers in LLM efficiency

## When to avoid
- need runnable software or a library rather than a paper list
- need production tooling for model compression
- require a licensed or citable software artifact

## Facets
- artifact type: learning-resource
- maturity: active
- function: llm-inference, llm-training, machine-learning, documentation
- domain: large-language-models, machine-learning, deep-learning, awesome-lists, tutorials
- platform: python, cross-platform
- tags: awesome-list, model-compression, quantization, knowledge-distillation, pruning, kv-cache, moe, inference-acceleration, curated-papers

## Member repositories
- horseee/Awesome-Efficient-LLM (main) score 41

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:08.041442+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 2026-08-30T02:59:19.693850+00:00, confidence not recorded.
  - readme: https://github.com/horseee/Awesome-Efficient-LLM (fetched 2026-08-28T04:06:08.041442+00:00, sha c08bbfad40e7)
- Data as of 2026-08-30T08:39:29.467469+00:00.