Together AI 成为 MiniMax M3 首选云伙伴，实现高效推理优化
原标题：Serving MiniMax-M3 for efficient inference: Unlocking 1M-Token Context and Multimodality Without Regrets
AI 摘要
Together AI 宣布成为 MiniMax M3 的首选云合作伙伴，将在其公开发布后托管该开放权重模型。Together AI 的推理和内核团队通过多项优化，如 KV-Block-Major 稀疏注意力内核、MSA 的分页注意力集成等，实现了 81-125% 的吞吐量提升。MiniMax M3 支持 1M 上下文窗口和原生多模态，其稀疏注意力机制显著加速了长上下文处理。
正文节选
- Together AI is the preferred cloud partner for MiniMax M3. Together AI will host the open-weights model as a developer endpoint upon its public release. - Our Inference and Kernel teams delivered significant engineering breakthroughs to serve M3 efficiently, including key optimizations such as a KV-Block-Major sparse attention kernel, a novel paged attention integration for MSA, highly optimized index scoring kernel and a Rust-based multimodal preprocessing gateway, resulting in 81–125% throug