8 papers
Communication-Aware Placement and Pruning for Efficient Mixture-of-Experts Inference
Xiao Shi, Yingying Sun, Jiangsu Du +2
As MoE models scale to hundreds of experts, placement and pruning decisions increasingly dictate communication volume, affecting the performance of distributed inference across GPU…
AlignedServe: Orchestrating Prefix-aware Batching to Build a High-throughput and Computing-efficient LLM Serving System
Fengyao Bai, Hongbin Zhang, Zhitao Chen +3
High-throughput inference serving is essential for applications built on large language models (LLMs). Existing serving frameworks reduce request-level and batch-level bubbles thro…
PipeMax: Enhancing Offline LLM Inference on Commodity GPU Servers
Hongbin Zhang, Taosheng Wei, Jiazhi Jiang +3
Offline LLM inference seeks to maximize request processing under fixed budgets, making commodity GPU servers a promising choice. However, prior work typically considers offloading…
POLAR-PIC: A Holistic Framework for Matrixized PIC with Co-Designed Compute, Layout, and Communication
Yizhuo Rao, Xingjian Cui, Shangzhi Pang +8
Particle-in-Cell (PIC) simulations are fundamental to plasma physics but often suffer from limited scalability due to particle-grid interaction bottlenecks and particle redistribut…
Matrix-PIC: Harnessing Matrix Outer-product for High-Performance Particle-in-Cell Simulations
Yizhuo Rao, Xingjian Cui, Jiabin Xie +5
Particle-in-Cell (PIC) simulations spend most of their execution time on particle--grid interactions, where fine-grained atomic updates become a major bottleneck on traditional man…
Boosting LLM Serving through Spatial-Temporal GPU Resource Sharing
Zejia Lin, Hongxin Xu, Guanyi Chen +3
Modern LLM serving systems confront inefficient GPU utilization due to the fundamental mismatch between compute-intensive prefill and memory-bound decode phases. While current prac…