arXiv (All)open access
SiliconBench: Speed, Memory, and Fidelity for LLM Serving on Unified-Memory Desktops
hardware architecture, distributed, parallel, and cluster computing, systems and control
This document is indexed with metadata only — full text is not available in the archive for this record.
Open the official source ↗
Record · ID 1013770
Retrieved via
Conceptio — every document is proof-bundled with source, license, and retrieval metadata.