# Multi-Bin Batching for Increasing LLM Inference Throughput

arXiv: https://arxiv.org/abs/2412.04504 · HTML: https://mlsanity.com/paper/2412.04504/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 39 references that are in the map.
- First posted on arXiv 3 Dec 2024.

## Builds on (most cited first, 29 of 29)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale](https://mlsanity.com/paper/2208.07339/) (2022)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://mlsanity.com/paper/2309.11998/) (2023)
- [How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering](https://mlsanity.com/paper/2012.00955/) (2020)
- [Llumnix: Dynamic Scheduling for Large Language Model Serving](https://mlsanity.com/paper/2406.03243/) (2024)
- [GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM](https://mlsanity.com/paper/2403.05527/) (2024)
- [Fast Distributed Inference Serving for Large Language Models](https://mlsanity.com/paper/2305.05920/) (2023)
- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2201.05273/) (2022)
- [Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline](https://mlsanity.com/paper/2305.13144/) (2023)
- [Efficient LLM Scheduling by Learning to Rank](https://mlsanity.com/paper/2408.15792/) (2024)
- [S3: Increasing GPU Utilization during Generative Inference for Higher Throughput](https://mlsanity.com/paper/2306.06000/) (2023)
- [Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction](https://mlsanity.com/paper/2404.08509/) (2024)
- [Queue management for slo-oriented large language model serving](https://mlsanity.com/paper/2407.00047/) (2024)
- [Enabling Efficient Batch Serving for LMaaS via Generation Length Prediction](https://mlsanity.com/paper/2406.04785/) (2024)
- [A Queueing Theoretic Perspective on Low-Latency LLM Inference with Variable Token Length](https://mlsanity.com/paper/2407.05347/) (2024)
- [Slice-Level Scheduling for High Throughput and Load Balanced LLM Serving](https://mlsanity.com/paper/2406.13511/) (2024)
- [Queueing Analysis of GPU-Based Inference Servers with Dynamic Batching: A Closed-Form Characterization](https://mlsanity.com/paper/1912.06322/) (2019)

## Built on by (most cited first, 9 of 9)

- [A Survey on Large Language Model Acceleration based on KV Cache Management](https://mlsanity.com/paper/2412.19442/) (2024)
- [TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling](https://mlsanity.com/paper/2508.17445/) (2025)
- [Infinite Sampling: Efficient and Stable Grouped RL Training for Large Language Models](https://mlsanity.com/paper/2506.22950/) (2025)
- [LAPS: A Length-Aware-Prefill LLM Serving System](https://mlsanity.com/paper/2601.11589/) (2026)
- [Equinox: Holistic Fair Scheduling in Serving Large Language Models](https://mlsanity.com/paper/2508.16646/) (2025)
- [A Queueing-Theoretic Framework for Stability Analysis of LLM Inference with KV Cache Memory Constraints](https://mlsanity.com/paper/2605.04595/) (2026)
- [DynaResize: Runtime GPU Reallocation for Disaggregated LLM Post-Training](https://mlsanity.com/paper/2607.22614/) (2026)
- [Parallelization Strategies for Dense LLM Deployment: Navigating Through Application-Specific Tradeoffs and Bottlenecks](https://mlsanity.com/paper/2603.05692/) (2026)
- [Boosting Embodied AI Agents through Perception-Generation Disaggregation and Asynchronous Pipeline Execution](https://mlsanity.com/paper/2509.09560/) (2025)

## Abstract (arXiv)

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.