# Past-Future Scheduler for LLM Serving under SLA Guarantees

arXiv: https://arxiv.org/abs/2507.10150 · HTML: https://mlsanity.com/paper/2507.10150/

## Key facts

- Cited by 20 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 18 of its 37 references that are in the map.
- First posted on arXiv 14 Jul 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, 18 of 18)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond](https://mlsanity.com/paper/1602.06023/) (2016)
- [Baichuan 2: Open Large-scale Language Models](https://mlsanity.com/paper/2309.10305/) (2023)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [A Deep Reinforced Model for Abstractive Summarization](https://mlsanity.com/paper/1705.04304/) (2017)
- [Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving](https://mlsanity.com/paper/2407.00079/) (2024)
- [DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference](https://mlsanity.com/paper/2401.08671/) (2024)
- [FlashDecoding++: Faster Large Language Model Inference on GPUs](https://mlsanity.com/paper/2311.01282/) (2023)
- [Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling](https://mlsanity.com/paper/2304.09145/) (2023)

## Built on by (most cited first, 20 of 20)

- [SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture](https://mlsanity.com/paper/2605.12500/) (2026)
- [TokenFlow: Responsive LLM Text Streaming Serving under Request Burst via Preemptive Scheduling](https://mlsanity.com/paper/2510.02758/) (2025)
- [ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression](https://mlsanity.com/paper/2603.17435/) (2026)
- [LLMC+: Benchmarking Vision-Language Model Compression with a Plug-and-play Toolkit](https://mlsanity.com/paper/2508.09981/) (2025)
- [A Survey on the Green Development of Large Models: From Resource-Efficient Architectures to Hardware-Software Co-Design](https://mlsanity.com/paper/2607.09084/) (2026)
- [Towards Resiliency in Large Language Model Serving with KevlarFlow](https://mlsanity.com/paper/2601.22438/) (2026)
- [FlowPrefill: Decoupling Preemption from Prefill Scheduling Granularity to Mitigate Head-of-Line Blocking in LLM Serving](https://mlsanity.com/paper/2602.16603/) (2026)
- [Astrolabe: Balancing Load in LLM Serving with Randomized Prediction-Guided Scheduling](https://mlsanity.com/paper/2508.03611/) (2025)
- [RepetitionCurse: Measuring and Understanding Router Imbalance in Mixture-of-Experts LLMs under DoS Stress](https://mlsanity.com/paper/2512.23995/) (2025)
- [SuperInfer: SLO-Aware Rotary Scheduling and Memory Management for LLM Inference on Superchips](https://mlsanity.com/paper/2601.20309/) (2026)
- [Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Framework](https://mlsanity.com/paper/2604.06170/) (2026)
- [LatencyPrism: Online Non-intrusive Latency Sculpting for SLO-Guaranteed LLM Inference](https://mlsanity.com/paper/2601.09258/) (2026)
- [PASCAL: A Phase-Aware Scheduling Algorithm for Serving Reasoning-based Large Language Models](https://mlsanity.com/paper/2602.11530/) (2026)
- [Mind the Delay: Latency-aware Query Routing for Heterogeneous LLM pools](https://mlsanity.com/paper/2607.18253/) (2026)
- [SageSched: Efficient LLM Scheduling Confronting Demand Uncertainty and Hybridity](https://mlsanity.com/paper/2603.07917/) (2026)
- [ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill](https://mlsanity.com/paper/2606.22541/) (2026)
- [Beyond Prefill-Decode Disaggregation: Dissecting LLM Inference for Heterogeneous Platforms via Dynamic Operator Scheduling](https://mlsanity.com/paper/2607.25498/) (2026)
- [NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement](https://mlsanity.com/paper/2607.26633/) (2026)
- [BALANCE: Hybrid Autoregressive-Speculative LLM Inference at the Network Edge](https://mlsanity.com/paper/2608.05926/) (2026)
- [TempoKV: Timely Staging of LLM KV Caches for Memory-Semantic Flash](https://mlsanity.com/paper/2609.35065/) (2026)

## Abstract (arXiv)

The exploration and application of Large Language Models (LLMs) is thriving. To reduce deployment costs, continuous batching has become an essential feature in current service frameworks. The effectiveness of continuous batching relies on an accurate estimate of the memory requirements of requests. However, due to the diversity in request output lengths, existing frameworks tend to adopt aggressive or conservative schedulers, which often result in significant overestimation or underestimation of memory consumption. Consequently, they suffer from harmful request evictions or prolonged queuing times, failing to achieve satisfactory throughput under strict Service Level Agreement (SLA) guarantees (a.k.a. goodput), across various LLM application scenarios with differing input-output length distributions. To address this issue, we propose a novel Past-Future scheduler that precisely estimates the peak memory resources required by the running batch via considering the historical distribution of request output lengths and calculating memory occupancy at each future time point. It adapts to applications with all types of input-output length distributions, balancing the trade-off between request queuing and harmful evictions, thereby consistently achieving better goodput. Furthermore, to validate the effectiveness of the proposed scheduler, we developed a high-performance LLM serving framework, LightLLM, that implements the Past-Future scheduler. Compared to existing aggressive or conservative schedulers, LightLLM demonstrates superior goodput, achieving up to 2-3× higher goodput than other schedulers under heavy loads. LightLLM is open source to boost the research in such direction (https://github.com/ModelTC/lightllm).