PrismServe: Efficient LLM Serving on Heterogeneous Accelerator Clusters

arXiv:2508.09204 · cs.LG, cs.AI, cs.CV · Submitted 2025-08-09 · Read on arXiv

cs.LG, cs.AI, cs.CV

Submitted: 2025-08-09

Updated: 2026-10-31

Code: https://github.com/paper-submission-goii/MoQE

Terminology

Sources

Related papers