Together AI Optimizes MiniMax-M3 for Efficient 1M-Token Context and Multimodal Inference

Jul 11, 2026

Together AI published a blog post detailing how it serves MiniMax-M3 efficiently, enabling 1M-token context and multimodality. The optimizations include KV-block-major sparse attention, paged MSA decode, optimized index scoring, and a Rust-based multimodal gateway.

Why it matters: This demonstrates practical techniques for deploying large multimodal models with long context windows, which is critical for enterprise applications requiring processing of extensive documents and multiple data types.

Full story at: Together AI Blog ↗