@article{flashprefillv2blocksparseprefillattentio, title = {FlashPrefill V2: Block-Sparse Prefill Attention for Long-Context LLM Serving}, author = {Qihang Fan and Huaibo Huang and Zhiying Wu and Bingning Wang and Ran He}, year = {2026}, eprint = {2608.19758}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.19758}, }