# BanaServe: Unified KV Cache and Dynamic Module Migration for Balancing Disaggregated LLM Serving in AI Infrastructure

arXiv: https://arxiv.org/abs/2510.13223 · HTML: https://mlsanity.com/paper/2510.13223/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Serving systems and request scheduling, one of 12 directions in Efficient LLM inference and serving.
- Builds on 28 of its 41 references that are in the map.
- First posted on arXiv 15 Oct 2025.

## Placed in

- Efficient LLM inference and serving / [Serving systems and request scheduling](https://mlsanity.com/inference/serving-systems-and-request-scheduling/)

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision](https://mlsanity.com/paper/2407.08608/) (2024)
- [Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs](https://mlsanity.com/paper/2310.01801/) (2023)
- [Orca: Progressive Learning from Complex Explanation Traces of GPT-4](https://mlsanity.com/paper/2306.02707/) (2023)
- [A Survey on Efficient Inference for Large Language Models](https://mlsanity.com/paper/2404.14294/) (2024)
- [Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving](https://mlsanity.com/paper/2407.00079/) (2024)
- [Llumnix: Dynamic Scheduling for Large Language Model Serving](https://mlsanity.com/paper/2406.03243/) (2024)
- [Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads](https://mlsanity.com/paper/2401.11181/) (2024)
- [LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism](https://mlsanity.com/paper/2404.09526/) (2024)
- [DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference](https://mlsanity.com/paper/2401.08671/) (2024)
- [SpotServe: Serving Generative Large Language Models on Preemptible Instances](https://mlsanity.com/paper/2311.15566/) (2023)
- [MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool](https://mlsanity.com/paper/2406.17565/) (2024)
- [BLITZSCALE: Fast and Live Large Model Autoscaling with O(1) Host Caching](https://mlsanity.com/paper/2412.17246/) (2024)
- [Generative Artificial Intelligence for Software Engineering -- A Research Agenda](https://mlsanity.com/paper/2310.18648/) (2023)
- [semi-PD: Towards Efficient LLM Serving via Phase-Wise Disaggregated Computation and Unified Storage](https://mlsanity.com/paper/2504.19867/) (2025)
- [KVDirect: Distributed Disaggregated LLM Inference](https://mlsanity.com/paper/2501.14743/) (2024)
- [NoCodeGPT: A No-Code Interface for Building Web Apps with Language Models](https://mlsanity.com/paper/2310.14843/) (2023)
- [StatuScale: Status-aware and Elastic Scaling Strategy for Microservice Applications](https://mlsanity.com/paper/2407.10173/) (2024)

## Built on by (most cited first, 3 of 3)

- [ThunderAgent: A Simple, Fast and Program-Aware Agentic Inference System](https://mlsanity.com/paper/2602.13692/) (2026)
- [GORGO: Online Tuning for Cross-Region Network-Aware LLM Serving](https://mlsanity.com/paper/2602.11688/) (2026)
- [Move the Query, Not the Cache: Characterizing Cross-Instance Latent Attention Redistribution Across GPU Fabrics](https://mlsanity.com/paper/2606.01502/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly deployed in AI infrastructure, driving the need for high throughput, resource efficient serving systems. Disaggregated LLM serving, which separates prompt prefill from auto-regressive decode, has emerged as a promising architecture by isolating their heterogeneous compute and memory demands. However, current disaggregated systems face three key limitations: (i) static resource allocation cannot adapt to highly dynamic workloads, causing over-provisioning that wastes resources or under-provisioning that violates service level objectives (SLOs); (ii) inherent load imbalance between prefill and decode stages, where prefill is compute-bound and decode is memory-bound, causes under-utilization in one tier while the other becomes a bottleneck; and (iii) prefix cache aware routing skews load distribution, as high cache hit rate prefill nodes attract disproportionately more requests, further degrading balance and efficiency. To address these issues, we present BanaServe, a dynamic orchestration framework that continuously rebalances computational and memory resources across prefill and decode instances while eliminating hotspots induced by cache. BanaServe introduces layer level weight migration, attention level Key Value Cache (KV Cache) migration, and Global KV Cache Store sharing with layer wise overlapped transmission, enabling both coarse grained (layer level) and fine grained (attention level) load redistribution with minimal latency overhead. These mechanisms allow routers to perform purely load aware scheduling, unconstrained by cache placement. Compared to vLLM, BanaServe achieves 1.2x-3.9x higher throughput with 3.9%-78.4% lower total processing time, and outperforms DistServe by 1.1x-2.8x in throughput with 1.4%-70.1% latency reduction.