{
  "title": "RMM",
  "total": 1,
  "posts": [
    {
      "title": "Algorithm Deep-Dive: RMM — TopK Column-Norm Slicing: Formulas, 1B–70B Results, and the Attention/MLP Asymmetry",
      "url": "/en/posts/deep-code-rmm/",
      "permalink": "https://hackcv.com/en/posts/deep-code-rmm/",
      "date": "2026-08-23",
      "author": "hackcv",
      "description": "RMM full breakdown: contraction-dim TopK column-norm selection, minimax optimality proof, retention-ratio knob; 8 benchmarks × 4 retention levels, attention vs MLP asymmetry data, A100 end-to-end 1.40× speedup.",
      "categories": ["Research Brief"],
      "tags": ["AI","Inference Optimization","Matrix Multiplication","RMM","Algorithm Deep-Dive"],
      "cover": "https://picsum.photos/seed/algorithm-deep-dive-rmm-topk-column-norm-slicing-formulas-1b70b-results-and-the-attention/mlp-asymmetry/1200/675",
      "readingTime": 3
    }
  ]
}