Author

X. Adettu

h-index 0 View on Semantic Scholar

We have 1 of 3 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.

StageML: Partial Evaluation for Multi-Tenant MoE-LoRA Inference

StageML, a partial evaluation (PE) system that exploits the temporal boundaries between deployment, adapter loading, tenant request admission, expert routing, and token generation using a binding-time lattice, and the results show that PE complements low-level kernel optimization.

X. Adettu, Tian Zhao · 0 citations