# gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling

arXiv: https://arxiv.org/abs/2504.14775 · HTML: https://mlsanity.com/paper/2504.14775/

## Key facts

- Cited by 5 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 37 of its 68 references that are in the map.
- First posted on arXiv 21 Apr 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, 30 of 37)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM](https://mlsanity.com/paper/2104.04473/) (2021)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [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)
- [The Falcon Series of Open Language Models](https://mlsanity.com/paper/2311.16867/) (2023)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision](https://mlsanity.com/paper/2407.08608/) (2024)
- [InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management](https://mlsanity.com/paper/2406.19707/) (2024)
- [GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers](https://mlsanity.com/paper/2402.19255/) (2024)
- [Memory-Efficient Pipeline-Parallel DNN Training](https://mlsanity.com/paper/2006.09503/) (2020)
- [PipeDream: Fast and Efficient Pipeline Parallel DNN Training](https://mlsanity.com/paper/1806.03377/) (2018)
- [DynamoLLM: Designing LLM Inference Clusters for Performance and Energy Efficiency](https://mlsanity.com/paper/2408.00741/) (2024)
- [MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark](https://mlsanity.com/paper/2405.12209/) (2024)
- [RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold](https://mlsanity.com/paper/2406.14532/) (2024)
- [Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving](https://mlsanity.com/paper/2405.12205/) (2024)
- [MathGenie: Generating Synthetic Data with Question Back-translation for Enhancing Mathematical Reasoning of LLMs](https://mlsanity.com/paper/2402.16352/) (2024)
- [VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street View](https://mlsanity.com/paper/2307.06082/) (2023)
- [SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient](https://mlsanity.com/paper/2301.11913/) (2023)
- [Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents](https://mlsanity.com/paper/2407.00993/) (2024)
- [Distributed Inference and Fine-tuning of Large Language Models Over The Internet](https://mlsanity.com/paper/2312.08361/) (2023)
- [Breaking the Computation and Communication Abstraction Barrier in Distributed Machine Learning Workloads](https://mlsanity.com/paper/2105.05720/) (2021)

## Built on by (most cited first, 5 of 5)

- [Towards Resiliency in Large Language Model Serving with KevlarFlow](https://mlsanity.com/paper/2601.22438/) (2026)
- [RouterWise: Joint Resource Allocation and Routing for Latency-Aware Multi-Model LLM Serving](https://mlsanity.com/paper/2604.10907/) (2026)
- [KV-Pipe: On the Relation Between KV Sharing and Pipeline Parallel Efficiency in LLMs](https://mlsanity.com/paper/2608.15943/) (2026)
- [WavePP: High-Throughput Pipeline Parallel LLM Prefill under Prefix Reuse](https://mlsanity.com/paper/2609.35263/) (2026)
- [Scaling LLM Inference via Parallelism: Throughput-Latency Trade-off](https://mlsanity.com/paper/2610.19405/) (2026)

## Abstract (arXiv)

Pipeline parallelism has emerged as a predominant approach for deploying large language models (LLMs) across distributed nodes, owing to its lower communication overhead compared to tensor parallelism. While demonstrating high throughput in request serving, pipeline parallelism often suffers from performance limitations caused by pipeline bubbles, which are primarily resulted from imbalanced computation delays across batches. Existing methods like Sarathi-Serve attempt to address this through hybrid scheduling of chunked prefill and decode tokens using a fixed token budget. However, such methods may experience significant fluctuations due to either insufficient prefill tokens or uneven distribution of decode tokens, ultimately leading to computational imbalance. To overcome these inefficiencies, we present gLLM, a globally balanced pipeline parallelism system incorporating Token Throttling to effectively mitigate the pipeline bubbles. Our Token Throttling mechanism is a fine-grained scheduling policy that independently regulates the quantities of prefill and decode tokens, thus enabling balanced computation by leveraging global information from the inference system. Specifically, for decode tokens, gLLM maintains near-consistent token count across processing batches. For prefill tokens, it dynamically adjusts batch sizes based on both total pending tokens and the memory utilization rates of key-value cache (KV cache). Furthermore, gLLM runtime adopts an asynchronous execution and message passing architecture specifically optimized for pipeline parallelism characteristics. Experimental evaluations with representative LLMs show that gLLM achieves significant performance improvements, delivering 11% to 398% higher maximum throughput compared to state-of-the-art pipeline or tensor parallelism systems, while simultaneously maintaining lower latency.