← Search

Shaoyuan Huang

2 accepted papers

2026

MAPS: Memory-Aware Predictive Scheduling Framework for Large Language Models Serving

ICML 2026poster

The surge of large language model (LLM) applications on personal devices imposes massive, bursty workloads on cloud serving infrastructure. While prefill-decode disaggregation improves throughput and scalability, memory-bound decode instances often suffer from persistent load imbalance, as output le…

Cited by 0SourceScholar
2024

EasyTS: The Express Lane to Long Time Series Forecasting

AAAI 2024technical

Responding to the escalating interest in long-term forecasting within the industry, we introduce EasyTS, a comprehensive toolkit engineered to streamline data collection, analysis, and model creation procedures. EasyTS acts as a unified solution, driving progress in long-term time series forecasting…