# Separius/awesome-fast-attention

list of efficient attention modules

Repository: https://github.com/Separius/awesome-fast-attention
Canonical: https://ross.abutalabs.com/products/awesome-fast-attention
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: transformer, attention, awesome, reformer, longformer, linformer, multihead-attention, self-attention, attention-is-all-you-need, transformer-network
Archived: true
Last push: 2021-08-23T09:58:15+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2224, "days_push": 1836, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1024, forks 106 (observed 2026-08-28T04:03:16.454876+00:00)

## What it is
A curated awesome-list of efficient attention modules for transformer models, cataloguing papers, implementations, computational complexity, and autoregressive support. It serves as a reference index linking to projects like Reformer, Longformer, Linformer, and other linear-complexity attention variants.

## Use cases
- find efficient attention implementations for long sequences
- compare complexity of transformer attention variants
- research alternatives to standard self-attention
- find longformer or linformer style implementations
- survey efficient attention papers for a literature review
- pick an attention module for a transformer project

## When to choose
- you need a quick index of efficient attention papers and their code
- you are researching sub-quadratic attention mechanisms
- you want to compare computational complexity across attention variants

## When to avoid
- you need a maintained, production-ready attention library
- you need up-to-date coverage of recent attention research (list last updated 2021)
- you want runnable code rather than links to other repositories

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, developer-tools
- domain: deep-learning, machine-learning
- platform: python
- tags: awesome-list, attention, transformer, efficient-attention, self-attention, long-context, curated-list, natural-language-processing

## Member repositories
- Separius/awesome-fast-attention (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:16.454876+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 2026-08-30T07:08:07.305210+00:00, confidence not recorded.
  - readme: https://github.com/Separius/awesome-fast-attention (fetched 2026-08-28T04:03:16.454876+00:00, sha d66cdb91b5b9)
- Data as of 2026-08-30T08:39:29.467469+00:00.