ParaAttention
by chengzeyi · GitHub
https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching
⭐ Stars
427
🍴 Forks
46
📜 License
—
License not specified📅 Created
2024
🔄 Last commit
1 yr ago
🏷️ Category
attention
💻 Language
You maintain this project?
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
📈 Star history
2026-07-202026-07-21
📄 About
https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching
❓ Frequently asked questions
What is ParaAttention?
https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching
Is ParaAttention open source?
ParaAttention is an open-source project.
Is ParaAttention free?
Yes. ParaAttention is free and open source — you can use, modify and self-host it.
🏅 Maintainer of this project?
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://opensourceai.tech/project/chengzeyi-paraattention.html)
🧬 Related projects🧬 View the DNA map →
annotated_deep_learning_paper_implementations
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including…
★ 67.1k · attention
sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
★ 30.6k · attention
numpy-ml
Machine learning, in numpy
★ 16.3k · attention