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

SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration

paper

Fields

id
sources/pap-attn-sageattention
URL
https://arxiv.org/abs/2410.02367
Publisher
arXiv
Kind
paper
Published
2024-10-03
Accessed
2026-10-03
notes
Strong venue evidence: arXiv journal_ref reads 'The Thirteenth International Conference on Learning Representations (ICLR 2025)'.

Notes

Strong venue evidence: arXiv journal_ref reads 'The Thirteenth International Conference on Learning Representations (ICLR 2025)'.

Cross-references

This record references no other records.