16 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…
Extreme-Scale Atomistic Simulation of Real-Temperature Magnetic Skyrmion Dynamics by Coupled Spin-Lattice Modeling
Pin Chen, Cheng-bing Chen, Hai Liu +9
Real-temperature topological magnetic dynamics in functional materials is governed by coupled lattice and spin evolution, yet remains inaccessible to predictive simulation at devic…
CodegenBench: Can LLMs Write Efficient Code Across Architectures?
Jie Li, Wenzhao Wu, Junqi Hu +5
While large language models (LLMs) have been extensively evaluated on code generation tasks for general-purpose programming and GPU-accelerated environments (e.g., PyTorch, CUDA),…
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…
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…
Beyond Few-Step Inference: Accelerating Video Diffusion Transformer Model Serving with Inter-Request Caching Reuse
Hao Liu, Ye Huang, Chenghuan Huang +5
Video Diffusion Transformer (DiT) models are a dominant approach for high-quality video generation but suffer from high inference cost due to iterative denoising. Existing caching…