CatKV: Accelerating Position-Independent Caching with Context-Adaptive KV Cache Compression

Summary: CatKV addresses remote KV-transfer bottlenecks in position-independent caching with context-adaptive SVD and latent-space quantization, tuned to each chunk’s spectrum. CPU-offloaded compression, grouped factorization, and pipelining yield 2–5× faster TTFT and 6–10× higher compression without accuracy loss. (summarized by gpt-6-luna on Oct 22 2026)

Paper ID: h8e4ce2118452e5e3
Venue: SIGMOD
Year: 2027
Pagerank: 4.9605343e-05
Overall Rank: 10,389 | 30.37%
DOI: 10.1145/3837104
PDF: Download (CC BY 4.0)

Incoming Non-self Citations Over Time

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

Authors

1. Jie Xu (Southern University of Science and Technology)
2. Renjie Liu (Southern University of Science and Technology)
3. Yi Li (Beijing Institute of Technology)
4. Bo Tang (Southern University of Science and Technology)

BibTeX Citation

@inproceedings{xu_sigmod27,
        title = {{CatKV: Accelerating Position-Independent Caching with Context-Adaptive KV Cache Compression}},
        author = {Xu, Jie and Liu, Renjie and Li, Yi and Tang, Bo},
        series = {{SIGMOD} '27},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3837104},
        url = {https://dl.acm.org/doi/10.1145/3837104},
        year = {2027}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank

Outgoing Citations (Sorted by Pagerank)

Showing 5 of 5 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
2,197	Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation	2025	SIGMOD	8.8751404e-05
5,142	Chameleon: a Heterogeneous and Disaggregated Accelerator System for Retrieval-Augmented Language Models	2025	VLDB	6.2420637e-05
5,376	RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference	2026	VLDB	6.139877e-05
6,455	AlayaDB: The Data Foundation for Efficient and Effective Long-context LLM Inference	2025	SIGMOD	5.762002e-05
6,944	DepCache: A KV Cache Management Framework for GraphRAG with Dependency Attention	2026	SIGMOD	5.6219388e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	5,376	RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference	2026	VLDB
2	3,844	HotPrefix: Hotness-Aware KV Cache Scheduling for Efficient Prefix Sharing in LLM Inference Systems	2026	SIGMOD
3	10,485	AlignedServe: Orchestrating Prefix-aware Batching to Build a High-throughput and Computing-efficient LLM Serving System	2026	SIGMOD
4	9,844	ContextCache: Context-Aware Semantic Cache for Multi-Turn Queries in Large Language Models	2025	VLDB
5	6,944	DepCache: A KV Cache Management Framework for GraphRAG with Dependency Attention	2026	SIGMOD
6	11,020	PolarKV: Tier Locally, Serve Globally- A KV Cache over Cloud Memory and Storage	2026	VLDB
7	2,197	Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation	2025	SIGMOD
8	10,847	Efficient Cooperation-Aware Key and Value Management for LLM Inference	2026	VLDB
9	10,549	KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference	2026	SIGMOD
10	3,972	PQCache: Product Quantization-based KVCache for Long Context LLM Inference	2025	SIGMOD