Author

Jun-Ming Zhang

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Sep 2026

EStream: Fast and Memory-Efficient MoE Prefill through Expert Virtualization on Mobile NPUs

EStream introduces a hardware-aware configuration algorithm that automatically configures the UFS--NPU pipeline and maximizes loading--computation overlap and introduces a hardware-aware configuration algorithm that automatically configures the UFS--NPU pipeline and maximizes loading--computation overlap.

Jun-Ming Zhang, Zhen-Zhe Zheng, Fan Wu et al. · 0 citations