inference/research
verifiedhigh · 0.95updated 2026-10-03

FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving

paper

Fields

id
sources/pap-attn-flashinfer-paper
URL
https://arxiv.org/abs/2501.01005
Publisher
arXiv
Kind
paper
Published
2025-01-02
Accessed
2026-10-03
notes
arXiv comment states 'Accepted by MLSys 2025'. Comment-field evidence, not independently confirmed via OpenReview.

Notes

arXiv comment states 'Accepted by MLSys 2025'. Comment-field evidence, not independently confirmed via OpenReview.

Cross-references

This record references no other records.