SiliconBench: Speed, Memory, and Fidelity for LLM Serving on Unified-Memory Desktops

Ranran Haoran Zhang, Aysa Xuemo Fan, David Munhá Correia +2

Concurrent local LLM serving on unified-memory desktops must preserve memory headroom and output fidelity, which speed-only rankings overlook. We introduce SiliconBench, which eval…