Lumai backs specialised hardware for AI prefill workloads

The Prefill Bottleneck in Disaggregated LLM Inference

Every request to a large language model runs through two very different phases: prefill and decode. Most infrastructure teams spend their time optimizing decode, the token-by-token generation everyone can see in a streaming response. Prefill gets less attention and for a growing share of workloads this is a mistake....