# LAPS: A Length-Aware-Prefill LLM Serving System

arXiv: https://arxiv.org/abs/2601.11589 · HTML: https://mlsanity.com/paper/2601.11589/

## Key facts

- Cited by 4 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 19 of its 30 references that are in the map.
- First posted on arXiv 4 Jan 2026.

## 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, 19 of 19)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees](https://mlsanity.com/paper/2406.16858/) (2024)
- [EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test](https://mlsanity.com/paper/2503.01840/) (2025)
- [ZeroSearch: Incentivize the Search Capability of LLMs without Searching](https://mlsanity.com/paper/2505.04588/) (2025)
- [SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills](https://mlsanity.com/paper/2308.16369/) (2023)
- [Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads](https://mlsanity.com/paper/2401.11181/) (2024)
- [A Comprehensive Survey of Dataset Distillation](https://mlsanity.com/paper/2301.05603/) (2023)
- [Universal Model Routing for Efficient LLM Inference](https://mlsanity.com/paper/2502.08773/) (2025)
- [Pollux: Co-adaptive Cluster Scheduling for Goodput-Optimized Deep Learning](https://mlsanity.com/paper/2008.12260/) (2020)
- [A Complete Survey on LLM-based AI Chatbots](https://mlsanity.com/paper/2406.16937/) (2024)
- [TensorOpera Router: A Multi-Model Router for Efficient LLM Inference](https://mlsanity.com/paper/2408.12320/) (2024)
- [P/D-Serve: Serving Disaggregated Large Language Model at Scale](https://mlsanity.com/paper/2408.08147/) (2024)
- [Multi-Bin Batching for Increasing LLM Inference Throughput](https://mlsanity.com/paper/2412.04504/) (2024)
- [Intelligent Router for LLM Workloads: Improving Performance Through Workload-Aware Load Balancing](https://mlsanity.com/paper/2408.13510/) (2024)
- [BucketServe: Bucket-Based Dynamic Batching for Smart and Efficient LLM Inference Serving](https://mlsanity.com/paper/2507.17120/) (2025)
- [Token Level Routing Inference System for Edge Devices](https://mlsanity.com/paper/2504.07878/) (2025)

## Built on by (most cited first, 4 of 4)

- [FleetOpt: Analytical Fleet Provisioning for LLM Inference with Compress-and-Route as Implementation Mechanism](https://mlsanity.com/paper/2603.16514/) (2026)
- [Characterization of Multi-Model Agentic AI Systems on General Tasks via Trace-Driven Simulation](https://mlsanity.com/paper/2606.01725/) (2026)
- [P-PAS: Prefill-Pressure Adaptive Scheduling for Long-Context LLM Serving](https://mlsanity.com/paper/2608.15171/) (2026)
- [Calibrate, Then Route: A Measured Study of Learned Request Routing for Disaggregated LLM Serving](https://mlsanity.com/paper/2609.16206/) (2026)

## Abstract (arXiv)

LAPS identifies and disaggregates requests with different prompt lengths in LLM serving to reduce TTFT latency. While recent systems have decoupled the prefill and decode stages to improve throughput, they still rely on unified scheduling policies that fail to adapt to heterogeneous workload characteristics. We observe that prompt-length variations lead to distinct performance bottlenecks, motivating an adaptive scheduling strategy. LAPS disaggregates multi-turn long-prefill requests from short-prefill ones and introduces a length-aware smart batching mechanism for short-prefill workloads. It adopts a dual-queue design that supports temporal disaggregation on a single prefill instance or spatial disaggregation across multiple instances. For short-prefill batches, a batch waiting window and CUDA Graph-based clustering mitigate interference from heterogeneous computation, reducing batching delay and lowering average latency. In real multi-turn workloads, LAPS reduces prefill latency by over 30% compared to vanilla SGLang under prefill-decode disaggregation, and further decreases SLO violations by 28% in multi-instance deployments with vanilla data-parallel configuration. Compared to the SGLang router with load balancing, it further lowers SLO violations by 12% in multi-GPU settings. Under high concurrency and mixed-request scenarios, LAPS improves request throughput by 35% serving Qwen2.5-32B model for prefill instance, demonstrating its effectiveness in optimizing heterogeneous LLM serving workloads.