2 papers
cs.LG2026
Efficient On-Device Diffusion LLM Inference with Mobile NPU
Tuowei Wang, Yanfan Sun, Ju Ren
Diffusion large language models (dLLMs) accelerate generation by denoising multiple tokens in parallel, making them attractive for latency-sensitive mobile inference. However, repe…
cs.LG2025
HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference
Shuzhang Zhong, Yanfan Sun, Ling Liang +3
The Mixture of Experts (MoE) architecture has demonstrated significant advantages as it enables to increase the model capacity without a proportional increase in computation. Howev…