FL

ByteDance-Seed/FlexPrefill

Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

168 9 +0/wk
GitHub
large-language-models natural-language-processing research sparse-attention
Trend 3

Star & Fork Trend (19 data points)

Stars
Forks

Multi-Source Signals

Growth Velocity

ByteDance-Seed/FlexPrefill has +0 stars this period . 7-day velocity: 0.6%.

Deep analysis is being generated for this repository.

Signal-backed technical analysis will be available soon.

Metric FlexPrefill ResearcherSkill flowcraft model2vec-rs
Stars 168 168168167
Forks 9 18917
Weekly Growth +0 +2+0+0
Language Python PythonTypeScriptRust
Sources 1 111
License Apache-2.0 MITMITMIT

Capability Radar vs ResearcherSkill

FlexPrefill
ResearcherSkill
Maintenance Activity 1

Last code push 178 days ago.

Community Engagement 27

Fork-to-star ratio: 5.4%. Lower fork ratio may indicate passive usage.

Issue Burden 70

Issue data not yet available.

Growth Momentum 30

No measurable growth in the current period (first-day cold start expected).

License Clarity 95

Licensed under Apache-2.0. Permissive — safe for commercial use.

Risk scores are computed from real-time repository data. Higher scores indicate healthier metrics.