FlashAttention
/All repositories
Overview
HEALTH SCORE
Excellent*
Partial score (2/3 categories)
56out of 65
Strong maintainer coverage. Development cadence is the only remaining gap. Security & Supply Chain is unavailable, so weights were redistributed.
LIFECYCLE
Active
Consistent commits, responsive maintainers, regular releases, and healthy issue triage.
Health breakdown
Excellent*(56/65)
Maintainer availability, known risks and supply chain posture, and whether the project is actively developed or appropriately stable.
Maintainer responsiveness
Median response time is 1 day.
Bus factor
38 active maintainers currently have merge rights.
Organization Diversity
Contributors span 763 organizations.
Project Achievements
Leaderboards
About
FlashAttention is a high-performance implementation of attention for training deep learning models, offering faster and more memory-efficient attention computation compared to standard implementations. It achieves this through a novel algorithm that reduces memory access and increases hardware utilization.
First commit
Software value
$4.1M
License(s)
BSD-3-Clause
Data sources
Git
GitHub