# CoCoScale: Leveraging Layer-wise Scaling to Unlock the Potential of Online LLM Serving

arXiv: https://arxiv.org/abs/2607.04181 · HTML: https://mlsanity.com/paper/2607.04181/

## 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 16 of its 39 references that are in the map.
- First posted on arXiv 5 Jul 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, 16 of 16)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (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)
- [LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks](https://mlsanity.com/paper/2412.15204/) (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)
- [Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads](https://mlsanity.com/paper/2401.11181/) (2024)
- [LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism](https://mlsanity.com/paper/2404.09526/) (2024)
- [BurstGPT: A Real-world Workload Dataset to Optimize LLM Serving Systems](https://mlsanity.com/paper/2401.17644/) (2024)
- [BLITZSCALE: Fast and Live Large Model Autoscaling with O(1) Host Caching](https://mlsanity.com/paper/2412.17246/) (2024)
- [HydraServe: Minimizing Cold Start Latency for Serverless LLM Serving in Public Clouds](https://mlsanity.com/paper/2502.15524/) (2025)
- [FlexPipe: Adapting Dynamic LLM Serving Through Inflight Pipeline Refactoring in Fragmented Serverless Clusters](https://mlsanity.com/paper/2510.11938/) (2025)
- [PipeOffload: Improving Scalability of Pipeline Parallelism with Memory Optimization](https://mlsanity.com/paper/2503.01328/) (2025)
- [Cloud-native and Distributed Systems for Efficient and Scalable Large Language Models -- A Research Agenda](https://mlsanity.com/paper/2604.17227/) (2026)

## Abstract (arXiv)

Online large language model (LLM) serving has become the backbone of modern AI applications, powering diverse downstream services through shared hardware clusters. However, modern serving systems frequently encounter highly dynamic workloads characterized by severe workload skewness, where a small fraction of model instances receives the vast majority of traffic. Existing instance-level scaling mechanisms are limited by coarse-grained resource adjustment: scaling up requires the cold-start of full-model replicas, incurring substantial latency, while scaling down leaves the system vulnerable to performance degradation during sudden traffic surges. The key insight of this work is that LLM serving offers a unique opportunity for fine-grained scaling. In this paper, we propose CoCoScale, a layer-wise dynamic scaling mechanism that selectively expands the parallelism of hot layers onto idle resources reclaimed from underutilized devices, enabling elastic data parallelism without altering model architectures or adding hardware overhead. Evaluations demonstrate that CoCoScale significantly reduces cold start latency by 97.9%-99.3% compared to traditional scale up. Under production traces, CoCoScale reduces average latency by 20.7%--28.1% and achieves full Service Level Objective (SLO) attainment, demonstrating superior dynamic adaptability and resource efficiency.