arXiv subjects

Chieh-Jan Mike Liang

Publications and source records attributed to Chieh-Jan Mike Liang.

6 recordsLinked to original sources

arXiv2026

OpScale: Operator-level Provisioning and Autoscaling for LLM Serving

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.

cs.DC↗

arXiv2026

MetaMuse: Algorithm Generation via Creative Ideation

Designing system algorithms remains challenging, where the discontinuous nature of the solution space often forces system engineers to rely on generic heuristics at the expense of performance. We study whether LLMs can practically drive algorithm generation, and find that they are biased towards well-known generic designs, rather than making the creative leaps needed to navigate the discontinuous solution space. To address this limitation, we introduce MetaMuse, a framework for creative ideation built on three self-reflection principles: (1) quantifying solution diversity and usefulness in measurable performance space, rather than abstract idea space, (2) steering ideation through external stimuli, rather than internal randomness, and (3) constructing executable solutions using waypoint reasoning, rather than free-form chain-of-thought. Considering two critical online problems at a global cloud provider, extensive evaluations show that MetaMuse can generate high-performing solutions: it reduces cache misses by up to 35.76% in cache replacement and reduces bin usage by up to 30.93% in online bin packing.

cs.AI↗

arXiv2025

From Models to Operators: Rethinking Autoscaling Granularity for Large Generative Models

Serving large generative models such as LLMs and multi- modal transformers requires balancing user-facing SLOs (e.g., time-to-first-token, time-between-tokens) with provider goals of efficiency and cost reduction. Existing solutions rely on static provisioning or model-level autoscaling, both of which treat the model as a monolith. This coarse-grained resource management leads to degraded performance or significant resource underutilization due to poor adaptability to dynamic inference traffic that is common online. The root cause of this inefficiency lies in the internal structure of generative models: they are executed as graphs of interconnected operators. Through detailed characterization and systematic analysis, we find that operators are heterogeneous in their compute and memory footprints and exhibit diverse sensitivity to workload and resource factors such as batch size, sequence length, and traffic rate. This heterogeneity suggests that the operator, rather than the entire model, is the right granularity for scaling decisions. We propose an operator-level autoscaling framework, which allocates resources at finer (operator)-granularity, optimizing the scaling, batching, and placement based on individual operator profiles. Evaluated on production-scale traces, our approach preserves SLOs with up to 40% fewer GPUs and 35% less energy, or under fixed resources achieves 1.6x higher throughput with 5% less energy. These results show that the operator, rather than the model, is fundamentally a more effective unit for scaling large generative workloads.

cs.DC↗

arXiv2024

DEX: Scalable Range Indexing on Disaggregated Memory [Extended Version]

Memory disaggregation can potentially allow memory-optimized range indexes such as B+-trees to scale beyond one machine while attaining high hardware utilization and low cost. Designing scalable indexes on disaggregated memory, however, is challenging due to rudimentary caching, unprincipled offloading and excessive inconsistency among servers. This paper proposes DEX, a new scalable B+-tree for memory disaggregation. DEX includes a set of techniques to reduce remote accesses, including logical partitioning, lightweight caching and cost-aware offloading. Our evaluation shows that DEX can outperform the state-of-the-art by 1.7--56.3X, and the advantage remains under various setups, such as cache size and skewness.

cs.DB↗

arXiv2024

Autothrottle: A Practical Bi-Level Approach to Resource Management for SLO-Targeted Microservices

Achieving resource efficiency while preserving end-user experience is non-trivial for cloud application operators. As cloud applications progressively adopt microservices, resource managers are faced with two distinct levels of system behavior: end-to-end application latency and per-service resource usage. Translating between the two levels, however, is challenging because user requests traverse heterogeneous services that collectively (but unevenly) contribute to the end-to-end latency. We present Autothrottle, a bi-level resource management framework for microservices with latency SLOs (service-level objectives). It architecturally decouples application SLO feedback from service resource control, and bridges them through the notion of performance targets. Specifically, an application-wide learning-based controller is employed to periodically set performance targets -- expressed as CPU throttle ratios -- for per-service heuristic controllers to attain. We evaluate Autothrottle on three microservice applications, with workload traces from production scenarios. Results show superior CPU savings, up to 26.21% over the best-performing baseline and up to 93.84% over all baselines.

cs.DC↗

arXiv2021

Wireless sensor network for in situ soil moisture monitoring

We discuss the history and lessons learned from a series of deployments of environmental sensors measuring soil parameters and CO2 fluxes over the last fifteen years, in an outdoor environment. We present the hardware and software architecture of our current Gen-3 system, and then discuss how we are simplifying the user facing part of the software, to make it easier and friendlier for the environmental scientist to be in full control of the system. Finally, we describe the current effort to build a large-scale Gen-4 sensing platform consisting of hundreds of nodes to track the environmental parameters for urban green spaces in Baltimore, Maryland.

eess.SY↗