verifiedhigh · 0.90updated 2026-10-03

vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention

paper

Fields

sources/pap-attn-vattention

URL

Publisher

arXiv

Kind

paper

Published

2024-05-07

Accessed

2026-10-03

notes

arXiv comment states 'To appear in ASPLOS 2025'.

arXiv comment states 'To appear in ASPLOS 2025'.

This record references no other records.