Hardware
MiniMax-M3 combines 1M context, native multimodality, and MiniMax Sparse Attention. The next layer is serving it efficiently: KV-block-major…
MiniMax-M3 combines 1M context, native multimodality, and MiniMax Sparse Attention. The next layer is serving it efficiently: KV-block-major sparse attention, paged MSA decode, optimized index scoring
MiniMax-M3 combines 1M context, native multimodality, and MiniMax Sparse Attention. The next layer is serving it efficiently: KV-block-major sparse attention, paged MSA decode, optimized index scoring, and multimodal preprocessing before the GPU worker. Together’s Inference and Kernel teams improved throughput by 81–125% across common agentic-shape traffic. We go deeper in this deep dive from @ywangfirstlean, @zhyncs42, @realDanFu and the team.
Source: Together AI (X) | 2026-06-02