Cerebras launches Cerebras Inference
Cerebras Inference launched
Why it matters
Used wafer-scale SRAM to get around the bandwidth limits of GPU HBM, popularizing the category of inference-only chips
Source — Primary sources first; secondary reports are labelled “Press”
Officialcerebras.aihttps://www.cerebras.ai/press-release/cerebras-launches-the-worlds-fastest-ai-inferenceAdded in Week 35, 2026 · See that week