inference/research
verifiedhigh · 0.85updated 2026-10-03

H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

paper

Fields

id
sources/pap-attn-h2o
URL
https://arxiv.org/abs/2306.14048
Publisher
arXiv
Kind
paper
Published
2023-06-24
Accessed
2026-10-03
notes
arXiv preprint; no journal_ref. Title renders as 'H$_2$O'.

Notes

arXiv preprint; no journal_ref. Title renders as 'H$_2$O'.

Cross-references

This record references no other records.