Hardware
Our inference stack, optimized for Blackwells, with a novel attention kernel and many new optimizations has started rolling out! It's alread…
Our inference stack, optimized for Blackwells, with a novel attention kernel and many new optimizations has started rolling out! It's already charting on Artificial Analysis, eg: #1 speed and latency
Our inference stack, optimized for Blackwells, with a novel attention kernel and many new optimizations has started rolling out! It's already charting on Artificial Analysis, eg: #1 speed and latency for @Kimi_Moonshot Kimi 2.6. #1 on latency on @MiniMax_AI, and miles ahead of other GPU endpoints. https://artificialanalysis.ai/models/kimi-k2-6/providers https://artificialanalysis.ai/models/minimax-m2-7/providers
Source: Together AI (X) | 2026-05-24