OrbitFlow: SLO-Aware Long-Context LLM Serving with Fine-Grained KV Cache Reconfiguration

Summary: OrbitFlow adaptively reconfigures per-request, per-layer KV-cache placement via runtime ILP decisions and feedback, rather than static offloading. Deferring memory-heavy requests preserves SLOs, cutting P95 latency 38% and delivering up to 3.3× throughput. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID: 14446
Venue: VLDB
Year: 2026
Pagerank: -
Overall Rank: 13,291 | 8.82%
DOI: 10.14778/3796195.3796214

Incoming Non-self Citations Over Time

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

Authors

1. Xinyue Ma (Pohang University of Science and Technology)
2. Heelim Hong (Ulsan National Institute of Science and Technology)
3. Taegeon Um (Samsung)
4. Jongseop Lee (Pohang University of Science and Technology)
5. Seoyeong Choy (Pohang University of Science and Technology)
6. Woo-Yeon Lee (Samsung)
7. Myeongjae Jeon (Pohang University of Science and Technology)

BibTeX Citation

@article{ma_vldb26,
        title = {{OrbitFlow: SLO-Aware Long-Context LLM Serving with Fine-Grained KV Cache Reconfiguration}},
        author = {Ma, Xinyue and Hong, Heelim and Um, Taegeon and Lee, Jongseop and Choy, Seoyeong and Lee, Woo-Yeon and Jeon, Myeongjae},
        journal = {PVLDB},
        series = {{VLDB} '26},
        volume = {19},
        number = {5},
        pages = {1046--1059},
        doi = {10.14778/3796195.3796214},
        url = {https://doi.org/10.14778/3796195.3796214},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank

Outgoing Citations (Sorted by Pagerank)

Showing 0 of 0 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	2,816	Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation	2025	SIGMOD
2	13,340	ContextCache: Context-Aware Semantic Cache for Multi-Turn Queries in Large Language Models	2025	VLDB
3	10,357	DepCache: A KV Cache Management Framework for GraphRAG with Dependency Attention	2026	SIGMOD
4	6,788	HotPrefix: Hotness-Aware KV Cache Scheduling for Efficient Prefix Sharing in LLM Inference Systems	2026	SIGMOD
5	10,228	Efficient LLM Serving for Agentic Workflows: A Data Systems Perspective	2026	SIGMOD
6	4,430	PQCache: Product Quantization-based KVCache for Long Context LLM Inference	2025	SIGMOD
7	10,191	AlignedServe: Orchestrating Prefix-aware Batching to Build a High-throughput and Computing-efficient LLM Serving System	2026	SIGMOD
8	13,288	Serving Hybrid LLM Loads with SLO Guarantees Using CPU-GPU Attention Piggybacking	2026	SIGMOD
9	10,259	KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference	2026	SIGMOD
10	6,900	Apt-Serve: Adaptive Request Scheduling on Hybrid Cache for Scalable LLM Inference Serving	2025	SIGMOD