DBScholar

Back to papers

PolarKV: Tier Locally, Serve Globally- A KV Cache over Cloud Memory and Storage

Summary: PolarKV is a cloud-native KV cache pairing co-located memory and block-storage shards, using memory for bandwidth and storage for capacity. Shard-local tiering avoids costly cross-VM movement and cuts LLM inference TTFT by up to 80%. (summarized by gpt-5.6-luna on Aug 28 2026)

Paper ID
h603b94f1ae37ef1c
Venue
VLDB
Year
2026
Pagerank
4.9793485e-05
Overall Rank
10,950 | 26.38%
DOI
10.14778/3827998.3828047

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

BibTeX Citation

@article{zhang_vldb26,
        title = {{PolarKV: Tier Locally, Serve Globally- A KV Cache over Cloud Memory and Storage}},
        author = {Zhang, Yingqiang and Yang, Xinjun and Chen, Hao and Li, Feifei and Wang, Shuwen and Sun, Chuan and Wu, Sai and Weng, Ninglong},
        journal = {PVLDB},
        series = {{VLDB} '26},
        volume = {19},
        number = {12},
        pages = {4480--4493},
        doi = {10.14778/3827998.3828047},
        url = {https://doi.org/10.14778/3827998.3828047},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank Citing Paper Year Venue Pagerank
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 8 of 8 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank Cited Paper Year Venue Pagerank
1,343 PolarDB Serverless: A Cloud Native Database for Disaggregated Data Centers 2021 SIGMOD 0.00010963588
1,398 SSD Bufferpool Extensions for Database Systems 2010 VLDB 0.00010783386
2,839 Turbocharging DBMS Buffer Pool Using SSDs 2011 SIGMOD 7.9506131e-05
3,028 Autoscaling Tiered Cloud Storage in Anna 2019 VLDB 7.7377953e-05
5,161 HotPrefix: Hotness-Aware KV Cache Scheduling for Efficient Prefix Sharing in LLM Inference Systems 2026 SIGMOD 6.2478968e-05
5,185 PolarDB-MP: A Multi-Primary Cloud-Native Database via Disaggregated Shared Memory 2024 SIGMOD 6.238732e-05
6,473 AlayaDB: The Data Foundation for Efficient and Effective Long-context LLM Inference 2025 SIGMOD 5.7739763e-05
7,945 Unlocking the Potential of CXL for Disaggregated Memory in Cloud-Native Databases 2025 SIGMOD 5.4212704e-05
Previous Page 1 / 1 Next

Semantically Similar Papers

# Overall Rank Paper Year Venue
1 10,407 AlignedServe: Orchestrating Prefix-aware Batching to Build a High-throughput and Computing-efficient LLM Serving System 2026 SIGMOD
2 13,581 OrbitFlow: SLO-Aware Long-Context LLM Serving with Fine-Grained KV Cache Reconfiguration 2026 VLDB
3 5,185 PolarDB-MP: A Multi-Primary Cloud-Native Database via Disaggregated Shared Memory 2024 SIGMOD
4 1,217 PolarFS: An Ultra-low Latency and Failure Resilient Distributed File System for Shared Storage Cloud Database 2018 VLDB
5 7,945 Unlocking the Potential of CXL for Disaggregated Memory in Cloud-Native Databases 2025 SIGMOD
6 1,343 PolarDB Serverless: A Cloud Native Database for Disaggregated Data Centers 2021 SIGMOD
7 5,161 HotPrefix: Hotness-Aware KV Cache Scheduling for Efficient Prefix Sharing in LLM Inference Systems 2026 SIGMOD
8 4,498 PQCache: Product Quantization-based KVCache for Long Context LLM Inference 2025 SIGMOD
9 10,776 Efficient Cooperation-Aware Key and Value Management for LLM Inference 2026 VLDB
10 10,472 KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference 2026 SIGMOD