4 papers
PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving
Zhongkai Yu, Ohm Rishabh Venkatachalam, Zheng Wang +9
Multi-LoRA serving is how one base model becomes thousands of specialized variants, one adapter per user, task, or agent, and the deployments can hold 1000-plus adapters. Serving t…
Patterns behind Chaos: Forecasting Data Movement for Efficient Large-Scale MoE LLM Inference
Zhongkai Yu, Yue Guan, Zihao Yu +6
Large-scale Mixture of Experts (MoE) Large Language Models (LLMs) have recently become the frontier open-weight models, achieving remarkable model capability similar to proprietary…
Unifews: You Need Fewer Operations for Efficient Graph Neural Networks
Ningyi Liao, Zihao Yu, Ruixiao Zeng +1
Graph Neural Networks (GNNs) have shown promising performance, but at the cost of resource-intensive operations on graph-scale matrices. To reduce computational overhead, previous…
DHIL-GT: Scalable Graph Transformer with Decoupled Hierarchy Labeling
Ningyi Liao, Zihao Yu, Siqiang Luo
Graph Transformer (GT) has recently emerged as a promising neural network architecture for learning graph-structured data. However, its global attention mechanism with quadratic co…