# ServerlessLLM: Low-Latency Serverless Inference for Large Language Models

arXiv: https://arxiv.org/abs/2401.14351 · HTML: https://mlsanity.com/paper/2401.14351/

## Key facts

- Cited by 80 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 83 references that are in the map.
- First posted on arXiv 25 Jan 2024.

## Builds on (most cited first, 19 of 19)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [Efficiently Scaling Transformer Inference](https://mlsanity.com/paper/2211.05102/) (2022)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [S-LoRA: Serving Thousands of Concurrent LoRA Adapters](https://mlsanity.com/paper/2311.03285/) (2023)
- [Fast Distributed Inference Serving for Large Language Models](https://mlsanity.com/paper/2305.05920/) (2023)
- [Serving DNNs like Clockwork: Performance Predictability from the Bottom Up](https://mlsanity.com/paper/2006.02464/) (2020)
- [Serverless in the Wild: Characterizing and Optimizing the Serverless Workload at a Large Cloud Provider](https://mlsanity.com/paper/2003.03423/) (2020)
- [Torpor: GPU-Enabled Serverless Computing for Low-Latency, Resource-Efficient Inference](https://mlsanity.com/paper/2306.03622/) (2023)
- [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)
- [Following the Data, Not the Function: Rethinking Function Orchestration in Serverless Computing](https://mlsanity.com/paper/2109.13492/) (2021)
- [FaaT: A Transparent Auto-Scaling Cache for Serverless Applications](https://mlsanity.com/paper/2104.13869/) (2021)

## Built on by (most cited first, 30 of 80)

- [MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism](https://mlsanity.com/paper/2504.02263/) (2025)
- [ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production](https://mlsanity.com/paper/2505.09999/) (2025)
- [ByteCheckpoint: A Unified Checkpointing System for Large Foundation Model Development](https://mlsanity.com/paper/2407.20143/) (2024)
- [Prism: Cost-Efficient Multi-LLM Serving via GPU Memory Ballooning](https://mlsanity.com/paper/2505.04021/) (2025)
- [Characterizing Mobile SoC for Accelerating Heterogeneous LLM Inference](https://mlsanity.com/paper/2501.14794/) (2025)
- [InstInfer: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference](https://mlsanity.com/paper/2409.04992/) (2024)
- [A Cost-Benefit Analysis of On-Premise Large Language Model Deployment: Breaking Even with Commercial LLM Services](https://mlsanity.com/paper/2509.18101/) (2025)
- [HydraServe: Minimizing Cold Start Latency for Serverless LLM Serving in Public Clouds](https://mlsanity.com/paper/2502.15524/) (2025)
- [RollArt: Disaggregated Multi-Task Agentic RL Training at Scale](https://mlsanity.com/paper/2512.22560/) (2025)
- [Semantic Caching for Low-Cost LLM Serving: From Offline Learning to Online Adaptation](https://mlsanity.com/paper/2508.07675/) (2025)
- [Slim-SC: Thought Pruning for Efficient Scaling with Self-Consistency](https://mlsanity.com/paper/2509.13990/) (2025)
- [TokenScale: Timely and Accurate Autoscaling for Disaggregated LLM Serving with Token Velocity](https://mlsanity.com/paper/2512.03416/) (2025)
- [KunServe: Parameter-centric Memory Management for Efficient Memory Overloading Handling in LLM Serving](https://mlsanity.com/paper/2412.18169/) (2024)
- [MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems](https://mlsanity.com/paper/2505.11415/) (2025)
- [HyGen: Efficient LLM Serving via Elastic Online-Offline Request Co-location](https://mlsanity.com/paper/2501.14808/) (2025)
- [ELIS: Efficient LLM Iterative Scheduling System with Response Length Predictor](https://mlsanity.com/paper/2505.09142/) (2025)
- [Mell: Memory-Efficient Large Language Model Serving via Multi-GPU KV Cache Management](https://mlsanity.com/paper/2501.06709/) (2025)
- [ContextPilot: Fast Long-Context Inference via Context Reuse](https://mlsanity.com/paper/2511.03475/) (2025)
- [Janus: Disaggregating Attention and Experts for Scalable MoE Inference](https://mlsanity.com/paper/2512.13525/) (2025)
- [ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression](https://mlsanity.com/paper/2603.17435/) (2026)
- [Opportunities and Challenges of Generative-AI in Finance](https://mlsanity.com/paper/2410.15653/) (2024)
- [MoE2: Optimizing Collaborative Inference for Edge Large Language Models](https://mlsanity.com/paper/2501.09410/) (2025)
- [MorphServe: Efficient and Workload-Aware LLM Serving via Runtime Quantized Layer Swapping and KV Cache Resizing](https://mlsanity.com/paper/2506.02006/) (2025)
- [Pythia: Exploiting Workflow Predictability for Efficient Agent-Native LLM Serving](https://mlsanity.com/paper/2604.25899/) (2026)
- [SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters](https://mlsanity.com/paper/2605.00528/) (2026)
- [SPORK: Self-Speculative Forking to Accelerate Agentic LLM Inference](https://mlsanity.com/paper/2607.03333/) (2026)
- [ConServe: Fine-Grained GPU Harvesting for LLM Online and Offline Co-Serving](https://mlsanity.com/paper/2410.01228/) (2024)
- [PolyServe: Efficient Multi-SLO Serving at Scale](https://mlsanity.com/paper/2507.17769/) (2025)
- [Efficient MoE Serving in the Memory-Bound Regime: Balance Activated Experts, Not Tokens](https://mlsanity.com/paper/2512.09277/) (2025)
- [WarmServe: Enabling One-for-Many GPU Prewarming for Multi-LLM Serving](https://mlsanity.com/paper/2512.09472/) (2025)

## Abstract (arXiv)

This paper presents ServerlessLLM, a distributed system designed to support low-latency serverless inference for Large Language Models (LLMs). By harnessing the substantial near-GPU storage and memory capacities of inference servers, ServerlessLLM achieves effective local checkpoint storage, minimizing the need for remote checkpoint downloads and ensuring efficient checkpoint loading. The design of ServerlessLLM features three core contributions: (i) fast multi-tier checkpoint loading, featuring a new loading-optimized checkpoint format and a multi-tier loading system, fully utilizing the bandwidth of complex storage hierarchies on GPU servers; (ii) efficient live migration of LLM inference, which enables newly initiated inferences to capitalize on local checkpoint storage while ensuring minimal user interruption; and (iii) startup-time-optimized model scheduling, which assesses the locality statuses of checkpoints on each server and schedules the model onto servers that minimize the time to start the inference. Comprehensive evaluations, including microbenchmarks and real-world scenarios, demonstrate that ServerlessLLM dramatically outperforms state-of-the-art serverless systems, reducing latency by 10 - 200X across various LLM inference workloads.