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

DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

paper

Fields

id
sources/pap-attn-duoattention
URL
https://arxiv.org/abs/2410.10819
Publisher
arXiv
Kind
paper
Published
2024-10-14
Accessed
2026-10-03
notes
arXiv preprint; no journal_ref.

Notes

arXiv preprint; no journal_ref.

Cross-references

This record references no other records.