---
schema_version: '1.0'
id: news-20260817-ef8b5f
title: Efficient Memory Management for Large Language Model Serving with PagedAttention
url: https://arxiv.org/abs/2309.06180
url_hash: ef8b5f9fca8456b539f4f2ab5d6ee5d83a65a9d1080b7138985c16509c920bfd
canonical_url: https://arxiv.org/abs/2309.06180
source: arxiv.org
category: news/tech
category_raw: it_ai
region: null
tags: []
lang: null
published_at: null
fetched_at: '2026-08-17T00:38:47.978684Z'
updated_at: '2026-08-17T00:39:14Z'
status: published
content_hash: null
content_changed_at: null
license_note: link-only
summary: null
summary_source: null
summary_en: null
summary_omitted_reason: license_restricted
redistribution: false
keywords_en:
- artificial intelligence
- Efficient
- Efficient Transformers
- for
- Forbes
- Language
- LanguageModel API
- Large
- Large Language Model (LLM
- Management
- Memory
- Memory Bandwidth
- Model
- ModelCompression
- Multi-model serving architectures
- PagedAttention
- Risk management
- Serving
- technology
- with
entities_en:
- name: Efficient Transformers
  type: method
- name: Forbes
  type: organization
- name: LanguageModel API
  type: organization
- name: Large Language Model (LLM
  type: artifact
- name: Memory Bandwidth
  type: concept
- name: ModelCompression
  type: concept
- name: Multi-model serving architectures
  type: method
- name: Risk management
  type: concept
topics_en:
- artificial intelligence
- technology
numeric_facts: []
entities:
- name: Memory Bandwidth
  type: concept
- name: Risk management
  type: concept
- name: Forbes
  type: organization
- name: Large Language Model (LLM
  type: artifact
- name: LanguageModel API
  type: organization
- name: ModelCompression
  type: concept
key_facts: []
related: []
related_auto:
- name: 50M Lightweight Models
  type: artifact
  weight: 1.0
- name: Adaptive safety model
  type: concept
  weight: 1.0
- name: Gradient Collapse Cascades
  type: concept
  weight: 1.0
- name: AdamW
  type: artifact
  weight: 1.0
computed_at: null
sanitized_at: '2026-08-20T14:56:50.092484+00:00'
---

# Efficient Memory Management for Large Language Model Serving with PagedAttention

## TL;DR
（要約なし・原文はリンク先を参照 / No summary available; see the source link.）

## Key Points
- (なし)

## Details
(本文なし。リンク先参照)

## Source
元記事: [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://arxiv.org/abs/2309.06180)