# Token Latency Fairness: Performance Isolation for Multi-Tenant LLM Serving

arXiv: https://arxiv.org/abs/2609.18112 · HTML: https://mlsanity.com/paper/2609.18112/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 40 references that are in the map.
- First posted on arXiv 16 Sep 2026.

## Builds on (most cited first, 16 of 16)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2505.16421/) (2025)
- [Vidur: A Large-Scale Simulation Framework For LLM Inference](https://mlsanity.com/paper/2405.05465/) (2024)
- [NanoFlow: Towards Optimal Large Language Model Serving Throughput](https://mlsanity.com/paper/2408.12757/) (2024)
- [Punica: Multi-Tenant LoRA Serving](https://mlsanity.com/paper/2310.18547/) (2023)
- [ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production](https://mlsanity.com/paper/2505.09999/) (2025)
- [Locality-aware Fair Scheduling in LLM Serving](https://mlsanity.com/paper/2501.14312/) (2025)
- [FairBatching: Fairness-Aware Batch Formation for LLM Inference](https://mlsanity.com/paper/2510.14392/) (2025)
- [BucketServe: Bucket-Based Dynamic Batching for Smart and Efficient LLM Inference Serving](https://mlsanity.com/paper/2507.17120/) (2025)
- [PecSched: Preemptive and Efficient Cluster Scheduling for LLM Inference](https://mlsanity.com/paper/2409.15104/) (2024)
- [Ensuring Fair LLM Serving Amid Diverse Applications](https://mlsanity.com/paper/2411.15997/) (2024)
- [SuperInfer: SLO-Aware Rotary Scheduling and Memory Management for LLM Inference on Superchips](https://mlsanity.com/paper/2601.20309/) (2026)
- [Delta Fair Sharing: Performance Isolation for Multi-Tenant Storage Systems](https://mlsanity.com/paper/2601.20030/) (2026)

## Abstract (arXiv)

LLM serving is typically offered as a shared, multi-tenant service, where high-demand workloads from one client can cause latency SLO violations for others. Existing solutions for performance isolation equalize client throughput in the long run, for example through queueing and batching fairness. However, these approaches do not provide latency isolation guarantees; as a result, well-behaved clients can still experience significant degradation to their token-level latencies. In this paper, we present FairInference, which provides the novel δ-token fairness guarantee: for a well-behaved client, if a token is generated in d time units in isolation, it will be generated within d + δ time units in multi-tenant execution, providing strong latency isolation guarantees for LLM serving. To achieve this, FairInference addresses a key challenge of LLM serving: bounding delays from sharing GPU resources without support for fine-grained scheduling or resource allocation. In FairInference, the scheduler enforces per-token deadlines, while bounding the delays from GPU compute sharing and accounting for the additional delays introduced by the shared KV caching in GPU memory. We show that FairInference effectively bounds token-level latency spikes for well-behaved clients and improves overall throughput compared to state-of-the-art LLM serving systems.