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

Summary: OrbitFlow: SLO-aware long-context LLM serving via adaptive, fine-grained KV-cache reconfiguration. Uses lightweight ILP + runtime feedback to choose per-request layer placements and defer memory-hungry in-flight requests, cutting offload-induced latency spikes and boosting SLO attainment. (summarized by gpt-5.4-mini on Apr 12 2026)

Paper ID: 14258
Venue: VLDB
Year: 2026
Pagerank: -
Overall Rank: 13,088 | 8.95%
DOI: 10.14778/3796195.3796214

Incoming Non-self Citations Over Time

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

Authors

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	Pagerank
9,103	AlayaDB: The Data Foundation for Efficient and Effective Long-context LLM Inference	2025	SIGMOD	4.3958197e-05
10,143	Beluga: A CXL-Based Memory Architecture for Scalable and Efficient LLM KVCache Management	2026	SIGMOD	4.1945683e-05
9,805	MEMO: Fine-grained Tensor Management For Ultra-long Context LLM Training	2025	SIGMOD	4.2805224e-05
10,222	RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference	2026	VLDB	4.1945683e-05
3,565	Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation	2025	SIGMOD	6.9655362e-05
13,135	ContextCache: Context-Aware Semantic Cache for Multi-Turn Queries in Large Language Models	2025	VLDB	-
10,066	DepCache: A KV Cache Management Framework for GraphRAG with Dependency Attention	2026	SIGMOD	4.1945683e-05
10,020	HotPrefix: Hotness-Aware KV Cache Scheduling for Efficient Prefix Sharing in LLM Inference Systems	2026	SIGMOD	4.1945683e-05
6,357	PQCache: Product Quantization-based KVCache for Long Context LLM Inference	2025	SIGMOD	5.0970739e-05
9,677	Apt-Serve: Adaptive Request Scheduling on Hybrid Cache for Scalable LLM Inference Serving	2025	SIGMOD	4.3047774e-05