Multi-Bin Batching for Increasing LLM Inference Throughput

[2412.04504] Multi-Bin Batching for Increasing LLM Inference Throughput Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computation and Language arXiv:2412.04504 (cs) [Submitted on 3 Dec 2024 ( v1 ), last revised 17 Aug 2026 (this version, v2)] Title: Multi-Bin Batching for Increasing LLM Inference Throughput Authors: Ozgur Guldogan , Jackson Kunde , Kangwook Lee , Ramtin Pedarsani View a PDF of the paper titled Multi-Bin Batching for Increasing LLM Inference Throughput, by Ozgur Guldogan and 3 other authors View PDF HTML (experimental) Abstract: As large language models (LLMs) grow in popularity for their diverse capabilities, improving the efficiency of their inference systems has become increasingly critical. Batching LLM requests is a critical step in scheduling the inference jobs on servers (e.g. GPUs), enabling the system to maximize throughput by allowing multiple requests to be processed in parallel. However, requests often have varying generation lengths, causing resource underutilization, as hardware must wait for the longest-running request in the batch to complete before moving to the next batch. We formalize this problem from a queueing-theoretic perspective, and aim to design a control policy which is throughput-optimal under a static-batching framework. We propose Multi-Bin Batching, a simple yet effective method that can provably improve LLM inference throughput under this framework by grouping requests with similar (predicted) execution times into predetermined bins. Through a combination of theoretical analysis and experiments, including real-world LLM inference scenarios with static and continuous-batching baselines, we demonstrate that multi-bin batching substantially improves throughput over static batching and quantify the remaining gap to native continuous batching under both oracle and estimated length information. Subjects: Computation and Language (cs.CL) ; Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG); Systems and Control (eess.SY) Cite as: arXiv:2412.04504 [cs.CL] (or arXiv:2412.04504v2 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2412.04504 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Ozgur Guldogan [ view email ] [v1] Tue, 3 Dec 2024 03:16:12 UTC (1,518 KB) [v2] Mon, 17 Aug 2026 00:01:33 UTC (1,164 KB) Full-text links: Access Paper: View a PDF of the paper titled Multi-Bin Batching for Increasing LLM Inference Throughput, by Ozgur Guldogan and 3 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL < prev | next > new | recent | 2024-12 Change to browse by: cs cs.DC cs.LG cs.SY eess eess.SY References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Multi-Bin Batching for Increasing LLM Inference Throughput#611271
• Distributed Generative Inference of LLM at Internet Scales with Multi-Dimensional Communication Optimization#126492
• FlashCP: Load-Balanced Communication-Efficient Context Parallelism for LLM Training#267627
• DeltaServe: Host-Agnostic Co-Serving of Inference and Fine-Tuning for LLMs#422230
• Frontier: Towards Comprehensive and Accurate LLM Inference Simulation#216791