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

SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization

paper

Fields

id
sources/pap-attn-sageattention2
URL
https://arxiv.org/abs/2411.10958
Publisher
arXiv
Kind
paper
Published
2024-11-17
Accessed
2026-10-03
notes
Strong venue evidence: arXiv journal_ref reads 'Proceedings of the 42nd International Conference on Machine Learning, PMLR 267, 2025 (ICML 2025)'.

Notes

Strong venue evidence: arXiv journal_ref reads 'Proceedings of the 42nd International Conference on Machine Learning, PMLR 267, 2025 (ICML 2025)'.

Cross-references

This record references no other records.