FlashInfer
/All repositories
Overview
HEALTH SCORE
Excellent
86out of 100
Strong maintainer coverage and development cadence. Security posture is the only remaining gap.
LIFECYCLE
Active
Consistent commits, responsive maintainers, regular releases, and healthy issue triage.
Health breakdown
Excellent(86/100)
Maintainer availability, known risks and supply chain posture, and whether the project is actively developed or appropriately stable.
Maintainer responsiveness
Median response time is 2 days.
Bus factor
131 active maintainers currently have merge rights.
Organization Diversity
Contributors span 578 organizations.
Project Achievements
Leaderboards
About
FlashInfer is a high-performance inference engine focused on optimizing attention computation for large language models (LLMs). It provides efficient CUDA kernels and implementations for accelerating attention mechanisms in transformer architectures.
First commit
Software value
$18M
Tags
attention
cuda
distributed-inference
gpu
jit
large-large-models
llm-inference
moe
nvidia
pytorch
License(s)
Apache-2.0
Data sources
Git
GitHub