For the first time in the MLPerf inference benchmarks, AMD posted numbers that don't require mental gymnastics to interpret.
Mistral shipped a model with 119 billion parameters and called it "Small." Under Apache 2.
Twelve months ago, if you asked an ML platform team what kept them up at night, the answer was GPU availability.
Q1 2026 delivered more custom inference silicon than any quarter in history. Google deployed Ironwood.