Broadcast, Don't Replicate: Eliminating Weight HBM in Datacenter LLM Serving

arXiv:2611.17097 · cs.AR, cs.DC, cs.ET, cs.NI · Submitted 2026-11-12 · Read on arXiv

cs.AR, cs.DC, cs.ET, cs.NI

Submitted: 2026-11-12

Updated: 2026-11-12

Terminology

Sources

Related papers