Engine-Agnostic Model Hot-Swapping for Cost-Effective LLM Inference.
Radostin Stoyanov, Viktria Spisakov, Adrian Reber, Wesley Armour, Marcin Copik, Rodrigo Bruno
Browse the full SC paper archive.
Radostin Stoyanov, Viktria Spisakov, Adrian Reber, Wesley Armour, Marcin Copik, Rodrigo Bruno
Browse the full SC paper archive.