← Search

Fan Dang

2 accepted papers

2026

DynamicInfer: Runtime-Aware Sparse Offloading for LLMs Inference on a Consumer-Grade GPU

ICLR 2026poster

Large Language Models (LLMs) have achieved remarkable success in various NLP tasks, but their enormous memory footprints pose significant challenges for deployment on consumer-grade GPUs. Prior solutions, such as PowerInfer, combine offloading and sparse activation to reduce memory and computational…

Cited by 0SourceScholar
2025

SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsity

CVPR 2025highlight

Despite the growing integration of deep models into mobile terminals, the accuracy of these models declines significantly due to various deployment interferences. Test-time adaptation (TTA) has emerged to improve the performance of deep models by adapting them to unlabeled target data online. Yet, t…