7 papers
SwarmX: Agentic Scheduling for Low-Latency Agentic Systems
Yeqi Huang, Yanwei Ye, Guomin Chen +8
Agentic AI applications compose multiple model calls and tool executions, creating new scheduling challenges for GPU-CPU clusters. Their inference time and model-call structure oft…
BatchGen: An Architecture for Scalable and Efficient Batch Inference
Tairan Xu, Leyang Xue, Zhan Lu +7
Batch inference has become a central mode of AI computation, yet existing inference engines still rely on execution models designed for interactive serving. When scaled to millions…
MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems
Yinsicheng Jiang, Yao Fu, Yeqi Huang +13
The sparse Mixture-of-Experts (MoE) architecture is increasingly favored for scaling Large Language Models (LLMs) efficiently, but it depends on heterogeneous compute and memory re…
MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems
Yinsicheng Jiang, Yao Fu, Yeqi Huang +13
The sparse Mixture-of-Experts (MoE) architecture is increasingly favored for scaling Large Language Models (LLMs) efficiently, but it depends on heterogeneous compute and memory re…
HybridServe: Efficient Serving of Large AI Models with Confidence-Based Cascade Routing
Leyang Xue, Yao Fu, Luo Mai +1
Giant Deep Neural Networks (DNNs), have become indispensable for accurate and robust support of large-scale cloud based AI services. However, serving giant DNNs is prohibitively ex…
MoE-Gen: High-Throughput MoE Inference on a Single GPU with Module-Based Batching
Tairan Xu, Leyang Xue, Zhan Lu +2
This paper presents MoE-Gen, a high-throughput MoE inference system optimized for single-GPU execution. Existing inference systems rely on model-based or continuous batching strate…