AlayaDB: The Data Foundation for Efficient and Effective Long-context LLM Inference
Authors:
- Yangshen DengYDYangshen Deng
- Zhengxin YouZYZhengxin You
- Long XiangLXLong Xiang
- Qilong LiQLQilong Li
- Peiqi YuanPYPeiqi Yuan
- Zhaoyang HongZHZhaoyang Hong
- Yitao ZhengYZYitao Zheng
- Wanting LiWLWanting Li
- Runzhong LiRLRunzhong Li
- Haotian LiuHLHaotian Liu
- Kyriakos MouratidisKMKyriakos Mouratidis
- Man Lung YiuMYMan Lung Yiu
Open Access
- 22 June 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 364-377
Abstract
No abstract availableAll Related Versions
Funding Information
- National Science Foundation of China (62422206, 62402420)
- Ministry of Education, Singapore (MOE-T2EP20121-0002)
- Hong Kong Research Grants Council (152043/23E)
This publication has 18 references indexed in Scilit:
- CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving2024
- ACORN: Performant and Predicate-Agnostic Search Over Vector Embeddings and Structured DataProceedings of the ACM on Management of Data, 2024
- Fast k-NN Graph Construction by GPU based NN-Descent2021
- Milvus2021
- Greenplum2021
- TiDBProceedings of the VLDB Endowment, 2020
- Fast approximate nearest neighbor search with the navigating spreading-out graphProceedings of the VLDB Endowment, 2019
- Amazon Aurora2017
- The Snowflake Elastic Data Warehouse2016
- System RACM Transactions on Database Systems, 1976