Self‑Evolving Specialized LLMs on HPC: Efficiency via 1‑bit Quantization and AI Computing Broker, Toward NPUs

Self‑Evolving Specialized LLMs on HPC: Efficiency via 1‑bit Quantization and AI Computing Broker, Toward NPUs

Wednesday, June 24, 2026 2:20 PM to 2:40 PM · 20 min. (Europe/Berlin)
Hall H, Booth L01 - Ground Floor
HPC Solutions Forum
Emerging Computing TechnologiesLarge Language Models and Generative AI in HPCResource Management and SchedulingSovereignty in AI

Information

Format
on-site