Startup claims to boost LLM performance using standard memory instead of GPU HBM — but experts remain unconvinced by the numbers despite promising CXL technology

When you purchase through links on our site, we may earn an affiliate commission.Heres how it works.

The company’s Memory Machine software uses CXL to reduce idle time in GPUs triggered by memory loading.

Impressive results

The demo utilized a high-throughput FlexGen generation engine and an OPT-66B large language model.

More from TechRadar Pro