# OpScale: Operator-level Provisioning and Autoscaling for LLM Serving

arXiv: https://arxiv.org/abs/2608.13499 · HTML: https://mlsanity.com/paper/2608.13499/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Serving systems and request scheduling, one of 12 directions in Efficient LLM inference and serving.
- Builds on 26 of its 55 references that are in the map.
- First posted on arXiv 13 Aug 2026.

## 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, 26 of 26)

- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [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)
- [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)
- [DynamoLLM: Designing LLM Inference Clusters for Performance and Energy Efficiency](https://mlsanity.com/paper/2408.00741/) (2024)
- [NanoFlow: Towards Optimal Large Language Model Serving Throughput](https://mlsanity.com/paper/2408.12757/) (2024)
- [ServerlessLLM: Low-Latency Serverless Inference for Large Language Models](https://mlsanity.com/paper/2401.14351/) (2024)
- [Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decoding](https://mlsanity.com/paper/2507.19427/) (2025)
- [MuxServe: Flexible Spatial-Temporal Multiplexing for Multiple LLM Serving](https://mlsanity.com/paper/2404.02015/) (2024)
- [POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference](https://mlsanity.com/paper/2410.18038/) (2024)
- [FIRM: An Intelligent Fine-Grained Resource Management Framework for SLO-Oriented Microservices](https://mlsanity.com/paper/2008.08509/) (2020)
- [Measuring Agents in Production](https://mlsanity.com/paper/2512.04123/) (2025)
- [MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism](https://mlsanity.com/paper/2504.02263/) (2025)
- [Serving Large Language Models on Huawei CloudMatrix384](https://mlsanity.com/paper/2506.12708/) (2025)
- [DeepServe: Serverless Large Language Model Serving at Scale](https://mlsanity.com/paper/2501.14417/) (2025)
- [semi-PD: Towards Efficient LLM Serving via Phase-Wise Disaggregated Computation and Unified Storage](https://mlsanity.com/paper/2504.19867/) (2025)
- [AIBrix: Towards Scalable, Cost-Effective Large Language Model Inference Infrastructure](https://mlsanity.com/paper/2504.03648/) (2025)
- [Expert-as-a-Service: Towards Efficient, Scalable, and Robust Large-scale MoE Serving](https://mlsanity.com/paper/2509.17863/) (2025)
- [Autothrottle: A Practical Bi-Level Approach to Resource Management for SLO-Targeted Microservices](https://mlsanity.com/paper/2212.12180/) (2022)
- [Hierarchical Autoscaling for Large Language Model Serving with Chiron](https://mlsanity.com/paper/2501.08090/) (2025)
- [LithOS: An Operating System for Efficient Machine Learning on GPUs](https://mlsanity.com/paper/2504.15465/) (2025)
- [HydraInfer: Hybrid Disaggregated Scheduling for Multimodal Large Language Model Serving](https://mlsanity.com/paper/2505.12658/) (2025)
- [Towards Efficient and Practical GPU Multitasking in the Era of LLM](https://mlsanity.com/paper/2508.08448/) (2025)
- [DDiT: Dynamic Resource Allocation for Diffusion Transformer Model Serving](https://mlsanity.com/paper/2506.13497/) (2025)

## Abstract (arXiv)

Achieving cost efficiency while meeting strict user-facing SLOs (e.g., time-to-first-token) remains a fundamental challenge for cloud GPU clusters serving large language models (LLMs). Autoscaling is the key mechanism for cluster resource management, yet a basic system design question is open for serving LLMs: what should be the unit of scaling? Existing approaches primarily treat the entire model as a monolithic scaling unit--simple but unable to capture the fine-grained dynamics of inference workloads. As a result, such coarse-grained scaling often leads to either SLO violations under bursty demand or significant GPU under-utilization. Our characterization reveals substantial operator heterogeneity, exposing operator-level elasticity as a viable scaling primitive. We present OpScale, a practical operator-level orchestration framework of profiling, provisioning, placement, and runtime serving. OpScale is designed to tackle the high complexity and the space explosion problem, arising from operating at this finer granularity. Evaluated with production traces on up to 40 A100s and 24 GB200s, OpScale attains SLOs with up to 36.3% fewer GPUs and 28% less power, or achieves 44% higher throughput under fixed cost budgets.