{"slug": "minimax-sparse-attention-per-group-block-selection-for-cheap-million-token", "title": "MiniMax Sparse Attention: Per-Group Block Selection for Cheap Million-Token Inference", "summary": "MiniMax introduced a sparse attention mechanism that selects per-group blocks to enable cost-effective inference on million-token sequences. The technique reduces computational overhead while maintaining model quality, potentially lowering the barrier for long-context AI applications.", "body_md": "Sorry, the page you're looking for doesn't exist\n\nThe page might have been moved, deleted, or never existed.\n\nHere are some helpful links:\n\nHome Page\n\nBlog Posts\n\nProjects\n\nBrowse by Tags\n\nContact Me", "url": "https://wpnews.pro/news/minimax-sparse-attention-per-group-block-selection-for-cheap-million-token", "canonical_source": "https://andlukyane.com/pages/Erlemar/artgor/blog/paper-review-minimax-sparse-attention", "published_at": "2026-06-15 00:00:00+00:00", "updated_at": "2026-06-15 19:34:40.284651+00:00", "lang": "en", "topics": ["large-language-models", "ai-research", "ai-infrastructure"], "entities": ["MiniMax"], "alternates": {"html": "https://wpnews.pro/news/minimax-sparse-attention-per-group-block-selection-for-cheap-million-token", "markdown": "https://wpnews.pro/news/minimax-sparse-attention-per-group-block-selection-for-cheap-million-token.md", "text": "https://wpnews.pro/news/minimax-sparse-attention-per-group-block-selection-for-cheap-million-token.txt", "jsonld": "https://wpnews.pro/news/minimax-sparse-attention-per-group-block-selection-for-cheap-million-token.jsonld"}}