FlexPrefill

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

What is FlexPrefill?

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

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/bytedance-seedflexprefill.svg)](https://yunodb.com/tools/bytedance-seedflexprefill?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/bytedance-seedflexprefill?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/bytedance-seedflexprefill.svg" alt="Featured on YunoDB" height="20"></a>