Lune

ASPLOS2026Top-tier venue

BlendServe: Optimizing Offline Inference with Resource-Aware Batching

Yilong Zhao, Shuo Yang, Kan Zhu, Lianmin Zheng, Baris Kasikci, Yifan Qiao, Yang Zhou, Jiarong Xing, Ion Stoica

Abstract

Offline batch inference is gaining popularity as a cost-effective solution for latency-insensitive tasks, such as model evaluation and data curation. As the latency objective is highly relaxed, maximizing throughput becomes the primary goal in offline inference. Previous studies focused solely on optimizing throughput within a batch. However, the diverse resource demands (compute-intensive vs. memory-intensive) across a wide range of applications make these approaches less effective, as imbalanced resource demands between batches restrict optimization opportunities.

Our insight for achieving optimal throughput is to reorder requests into batches that mix compute-and memoryintensive workloads to maximize resource overlap. However, such a request schedule can conflict with the schedule that maximizes prefix sharing, a widely-used performance optimization, causing suboptimal inference throughput. In this paper, we first build a performance model to analyze request resource demands. Based on it, we design BlendServe, which harmonizes both resource overlapping and prefix sharing to maximize throughput. BlendServe organizes all requests using a resource-aware prefix tree and proposes a dual scanning algorithm to obtain the request schedule. Our evaluation on various models and workloads shows that BlendServe can achieve up to 90% of the optimal throughput.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Tree of Thoughts: Deliberate Problem Solving with Large Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • SGLang: Efficient Execution of Structured Language Model Programs cites Tree of Thoughts: Deliberate Problem Solving with Large Language Models
  • SGLang: Efficient Execution of Structured Language Model Programs cites Measuring Massive Multitask Language Understanding
  • SGLang: Efficient Execution of Structured Language Model Programs cites Efficient Memory Management for Large Language Model Serving with PagedAttention
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on34

  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  2. Measuring Massive Multitask Language UnderstandingDan Hendrycks, Collin Burns, Steven Basart, Andy Zou et al.ICLR 2021 · 7,905 citations
  3. Tree of Thoughts: Deliberate Problem Solving with Large Language ModelsShunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran et al.NeurIPS 2023 · 5,068 citations
  4. SGLang: Efficient Execution of Structured Language Model ProgramsLianmin Zheng, Liangsheng Yin, Zhiqiang Xie, Chuyue Sun et al.NeurIPS 2024 · 1,586 citations
  5. Efficient Memory Management for Large Language Model Serving with PagedAttentionWoosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng et al.SOSP 2023 · 1,016 citations

Related papers

  1. Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-ServeAmey Agrawal, Nitin Kedia, Ashish Panwar, Jayashree Mohan et al.OSDI 2024 · 537 citations
  2. BROS: Efficient LLM Serving on Hybrid Real-time and Best-effort RequestsBorui Wan, Juntao Zhao, Chenyu Jiang, Chuanxiong Guo et al.INFOCOM 2026 · 1 citation
  3. AlignedServe: Orchestrating Prefix-aware Batching to Build a High-throughput and Computing-efficient LLM Serving SystemFengyao Bai, Hongbin Zhang, Zhitao Chen, Jiangsu Du et al.SIGMOD 2026 · 3 citations
  4. QoServe: Breaking the Silos of LLM Inference ServingKanishk Goel, Jayashree Mohan, Nipun Kwatra, Ravi Shreyas Anupindi et al.ASPLOS 2026 · 3 citations
  5. Batched in Back: Characterizing and Optimizing Offline LLM Inference in Production with ACDCLeping Yang, Xue Li, Kun Qian, Erci Xu et al.SOSP 2026
Dusk over the sea between two cliffs drawn in fine vertical lines