MiniMax introduced sparse key-value caches that reduce attention scaling from quadratic to near-linear, enabling practical multi-hundred-kilobyte context windows on a single GPU. The method cuts per-t…
MiniMax released MSA (MiniMax Sparse Attention), a block-sparse attention method that reduces the quadratic cost of softmax attention at long contexts. The method was trained on a 109B-parameter Mixtu…
MiniMax M3, the company's first model with a 1M-token context window and native multimodality, is now available on Vercel AI Gateway. The model, built around MiniMax Sparse Attention, improves softwar…
A developer is building ScopeAuditor.com, a privacy-first tool designed to analyze Statements of Work for scope creep before contracts are signed. The tool operates on a zero-retention pipeline, proce…