# FastSwitch: Optimizing Context Switching Efficiency in Fairness-aware Large Language Model Serving

arXiv: https://arxiv.org/abs/2411.18424 · HTML: https://mlsanity.com/paper/2411.18424/

## Key facts

- Cited by 5 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 25 of its 37 references that are in the map.
- First posted on arXiv 27 Nov 2024.

## 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, 25 of 25)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [Large Language Models: A Survey](https://mlsanity.com/paper/2402.06196/) (2024)
- [Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs](https://mlsanity.com/paper/2310.01801/) (2023)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [Generating Images with Multimodal Language Models](https://mlsanity.com/paper/2305.17216/) (2023)
- [CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving](https://mlsanity.com/paper/2310.07240/) (2023)
- [SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills](https://mlsanity.com/paper/2308.16369/) (2023)
- [Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis](https://mlsanity.com/paper/2304.04675/) (2023)
- [Fast Distributed Inference Serving for Large Language Models](https://mlsanity.com/paper/2305.05920/) (2023)
- [Fairness in Serving Large Language Models](https://mlsanity.com/paper/2401.00588/) (2023)
- [Andes: Defining and Enhancing Quality-of-Experience in LLM-Based Text Streaming Services](https://mlsanity.com/paper/2404.16283/) (2024)
- [From LLM to Conversational Agent: A Memory Enhanced Architecture with Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2401.02777/) (2024)
- [Queue management for slo-oriented large language model serving](https://mlsanity.com/paper/2407.00047/) (2024)
- [Understanding Power Consumption and Reliability of High-Bandwidth Memory with Voltage Underscaling](https://mlsanity.com/paper/2101.00969/) (2020)

## Built on by (most cited first, 5 of 5)

- [A Survey on Large Language Model Acceleration based on KV Cache Management](https://mlsanity.com/paper/2412.19442/) (2024)
- [Scorpio: Serving Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference](https://mlsanity.com/paper/2505.23022/) (2025)
- [Priority-Aware Preemptive Scheduling for Mixed-Priority Workloads in MoE Inference](https://mlsanity.com/paper/2503.09304/) (2025)
- [Towards Multi-Model LLM Schedulers: Empirical Insights into Offloading and Preemption](https://mlsanity.com/paper/2605.19593/) (2026)
- [Does Execution Require Target KV Fidelity? A Mixed-Fidelity KV Runtime for LLM Serving](https://mlsanity.com/paper/2609.33536/) (2026)

## Abstract (arXiv)

Serving numerous users and requests concurrently requires good fairness in Large Language Models (LLMs) serving system. This ensures that, at the same cost, the system can meet the Service Level Objectives (SLOs) of more users , such as time to first token (TTFT) and time between tokens (TBT), rather than allowing a few users to experience performance far exceeding the SLOs. To achieve better fairness, the preemption-based scheduling policy dynamically adjusts the priority of each request to maintain balance during runtime. However, existing systems tend to overly prioritize throughput, overlooking the overhead caused by preemption-induced context switching, which is crucial for maintaining fairness through priority adjustments. In this work, we identify three main challenges that result in this overhead. 1) Inadequate I/O utilization. 2) GPU idleness. 3) Unnecessary I/O transmission during multi-turn conversations. Our key insight is that the block-based KV cache memory policy in existing systems, while achieving near-zero memory waste, leads to discontinuity and insufficient granularity in the KV cache memory. To respond, we introduce FastSwitch, a fairness-aware serving system that not only aligns with existing KV cache memory allocation policy but also mitigates context switching overhead. Our evaluation shows that FastSwitch outperforms the state-of-the-art LLM serving system vLLM with speedups of 1.4-11.2x across different tail TTFT and TBT.