Lumai’s Iris Nova is purpose-built to accelerate AI prefill workloads, freeing GPU capacity for token generation and making existing infrastructure more productive without requiring wholesale replacement. In Lumai testing, Iris Nova ran billion-parameter LLMs in real time and demonstrated approximately 10× more compute per watt than GPU-based equivalents on prefill workloads.
Lumai’s Iris Nova is purpose-built to accelerate AI prefill workloads, freeing GPU capacity for token generation and making existing infrastructure more productive without requiring wholesale replacement. In Lumai testing, Iris Nova ran billion-parameter LLMs in real time and demonstrated approximately 10× more compute per watt than GPU-based equivalents on prefill workloads.