SP

thu-ml/SpargeAttn

[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.

973 91 +0/wk
GitHub
ai-infra attention inference-acceleration llm mlsys quantization sageattention sparse-attention video-generation vision-transformer vit
Trend 0

Star & Fork Trend (17 data points)

Stars
Forks

Multi-Source Signals

Growth Velocity

thu-ml/SpargeAttn has +0 stars this period . Velocity data will be available after more historical data is collected.

Deep analysis is being generated for this repository.

Signal-backed technical analysis will be available soon.

Metric SpargeAttn awesome-devops-mcp-servers keras-hub AIAS
Stars 973 973972972
Forks 91 231331291
Weekly Growth +0 +1+0+1
Language Cuda N/APythonJava
Sources 1 111
License Apache-2.0 MITApache-2.0Apache-2.0

Capability Radar vs awesome-devops-mcp-servers

SpargeAttn
awesome-devops-mcp-servers
Maintenance Activity 79

Last code push 43 days ago.

Community Engagement 47

Fork-to-star ratio: 9.4%. 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.