# he-y/Awesome-Pruning

A curated list of neural network pruning resources.

Repository: https://github.com/he-y/Awesome-Pruning
Canonical: https://ross.abutalabs.com/products/awesome-pruning
License Family: other
Topics: pruning, model-compression, model-acceleration, awesome-list
Last push: 2024-04-04T07:18:56+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2652, "days_push": 881, "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 2497, forks 332 (observed 2026-08-28T04:06:56.766085+00:00)

## What it is
A curated awesome-list of neural network pruning resources, including papers organized by year and pruning type (filter, weight, special networks), plus a structured pruning survey. It serves as a research reference rather than a runnable tool.

## Use cases
- find papers on neural network pruning
- learn about structured pruning for CNNs
- research model compression techniques
- find pruning papers with code implementations
- survey filter and weight pruning methods
- keep up with model acceleration research

## When to choose
- you need a comprehensive, categorized bibliography of pruning research
- you are surveying model compression literature by year or technique
- you want links to pruning papers with available code

## When to avoid
- you need runnable pruning or compression software
- you want a tutorial or hands-on implementation guide
- you need non-pruning compression methods like quantization or distillation

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, deep-learning
- domain: deep-learning, machine-learning, awesome-lists
- platform: cross-platform
- tags: neural-network-pruning, model-compression, model-acceleration, curated-list, papers

## Member repositories
- he-y/Awesome-Pruning (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:56.766085+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 2026-08-30T02:27:08.228834+00:00, confidence not recorded.
  - readme: https://github.com/he-y/Awesome-Pruning (fetched 2026-08-28T04:06:56.766085+00:00, sha ac0930dacdf2)
- Data as of 2026-08-30T08:39:29.467469+00:00.