Unverified70% confidenceFactExact time

Continuous batching was systematically proposed in the 2023 PagedAttention paper from UC Berkeley.

2

Sources

70%

Confidence

Long-term

Relevance

7/13/2026

First Seen

Sources

分布式AI系统：训练、推理与生产部署工程实践指南

Related Claims

Unverified斯坦福大学研究团队在2022年的综述论文中系统记录了模型的涌现能力现象76% similar UnverifiedPagedAttention 由 UC Berkeley vLLM 团队于 2023 年提出，可消除传统连续预分配模式下高达 60-80% 的显存碎片浪费74% similar VerifiedThe term "foundation model" was formally introduced by Stanford University's HAI Institute in 2021.67% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/502861

API

curl https://kongchang.com/api/v1/knowledge/claims/502861

MCP

get_claim(id=502861)