Author

Simon Wu

h-index 0 View on Semantic Scholar

We have 1 of 2 papers

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.

Book Open access Jul 2026

Phase-aware Peak Power Reduction for Minimizing the Capital Expense of LLM Inference

PPPR is proposed, a Phase-aware Peak Power Reduction framework for minimizing the CapEx of LLM inference that features two novel LLM-specific designs and phase-aware timing that shaves more peak power and leads to lower CapEx.

Simon Wu, Yuan Ma, Xiaorui Wang · International Conference on... · 0 citations