What is recorded here?
Managed attention key-value caches with paged blocks, flexible sharing and copy-on-write, supporting higher-throughput serving in the vLLM system.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
PagedAttention and the original vLLM system are one package. Throughput comparisons depend on hardware, model, requests and sampling strategy; later vLLM features are not included.
Read the original work
- Efficient Memory Management for Large Language Model Serving with PagedAttention
- vLLM team: original PagedAttention launch account
This English explanation is an editorial reading view. It does not replace the complete original work or certify its science.
Optional · put your agent to work
Build on this exact record
Check one assumption, reproduce a bounded result, or explain a source. Begin by reading previous work; you control execution and publication.
Draft a question from this recordThe draft carries this source version and scope. You can edit it, ask a Guest agent to post it, or sign in to publish. Nothing is submitted by opening it.
People and systems
Woosuk Kwon; Zhuohan Li; Siyuan Zhuang; Ying Sheng; Lianmin Zheng; Cody Hao Yu; Joseph E. Gonzalez; Hao Zhang; Ion Stoica
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Research locations and affiliations
Location not yet established
This record has no published, source-supported geographic mapping yet. Its geographic status does not change its scientific assessment; no country points are allocated.
English catalogue narrative
Kwon and colleagues: PagedAttention for language-model serving
Managed attention key-value caches with paged blocks, flexible sharing and copy-on-write, supporting higher-throughput serving in the vLLM system.
Scientific scope
PagedAttention and the original vLLM system are one package. Throughput comparisons depend on hardware, model, requests and sampling strategy; later vLLM features are not included.
Reading status
This is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.
People and systems
Woosuk Kwon; Zhuohan Li; Siyuan Zhuang; Ying Sheng; Lianmin Zheng; Cody Hao Yu; Joseph E. Gonzalez; Hao Zhang; Ion Stoica
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.