# PipeBoost: Resilient Pipelined Architecture for Fast Serverless LLM Scaling

arXiv: https://arxiv.org/abs/2503.17707 · HTML: https://mlsanity.com/paper/2503.17707/

## Key facts

- Cited by 2 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 28 of its 57 references that are in the map.
- First posted on arXiv 22 Mar 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, 28 of 28)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [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)
- [Ray: A Distributed Framework for Emerging AI Applications](https://mlsanity.com/paper/1712.05889/) (2017)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving](https://mlsanity.com/paper/2407.00079/) (2024)
- [Llumnix: Dynamic Scheduling for Large Language Model Serving](https://mlsanity.com/paper/2406.03243/) (2024)
- [Memory-Efficient Pipeline-Parallel DNN Training](https://mlsanity.com/paper/2006.09503/) (2020)
- [MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs](https://mlsanity.com/paper/2402.15627/) (2024)
- [LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism](https://mlsanity.com/paper/2404.09526/) (2024)
- [DAPPLE: A Pipelined Data Parallel Approach for Training Large Models](https://mlsanity.com/paper/2007.01045/) (2020)
- [TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models](https://mlsanity.com/paper/2102.07988/) (2021)
- [Serverless in the Wild: Characterizing and Optimizing the Serverless Workload at a Large Cloud Provider](https://mlsanity.com/paper/2003.03423/) (2020)
- [Bamboo: Making Preemptible Instances Resilient for Affordable Training of Large DNNs](https://mlsanity.com/paper/2204.12013/) (2022)
- [Characterization of Large Language Model Development in the Datacenter](https://mlsanity.com/paper/2403.07648/) (2024)
- [Benchmarking, Analysis, and Optimization of Serverless Function Snapshots](https://mlsanity.com/paper/2101.09355/) (2021)
- [No Provisioned Concurrency: Fast RDMA-codesigned Remote Fork for Serverless Computing](https://mlsanity.com/paper/2203.10225/) (2022)
- [Faasm: Lightweight Isolation for Efficient Stateful Serverless Computing](https://mlsanity.com/paper/2002.09344/) (2020)
- [FaaSNet: Scalable and Fast Provisioning of Custom Serverless Container Runtimes at Alibaba Cloud Function Compute](https://mlsanity.com/paper/2105.11229/) (2021)
- [ENOVA: Autoscaling towards Cost-effective and Stable Serverless LLM Serving](https://mlsanity.com/paper/2407.09486/) (2024)

## Built on by (most cited first, 2 of 2)

- [TokenScale: Timely and Accurate Autoscaling for Disaggregated LLM Serving with Token Velocity](https://mlsanity.com/paper/2512.03416/) (2025)
- [WarmServe: Enabling One-for-Many GPU Prewarming for Multi-LLM Serving](https://mlsanity.com/paper/2512.09472/) (2025)

## Abstract (arXiv)

This paper presents PipeBoost, a low-latency LLM serving system for multi-GPU (serverless) clusters, which can rapidly launch inference services in response to bursty requests without preemptively over-provisioning GPUs. Many LLM inference tasks rely on the same base model (e.g., LoRA). To leverage this, PipeBoost introduces fault-tolerant pipeline parallelism across both model loading and inference stages. This approach maximizes aggregate PCIe bandwidth and parallel computation across GPUs, enabling faster generation of the first token. PipeBoost also introduces recovery techniques that enable uninterrupted inference services by utilizing the shared advantages of multiple GPUs. Experimental results show that, compared to state-of-the-art low-latency LLM serving systems, PipeBoost reduces inference latency by 31% to 49.8%. For certain models (e.g., OPT-1.3B), PipeBoost achieves cold-start latencies in the range of a few hundred microseconds.