https://mbrenndoerfer.com/writing/switch-transformer-top-1-routing-trillion-parameter-scaling/switch-transformer2026-01-05T17:34:32.000Zhttps://mbrenndoerfer.com/writing/switch-transformer-top-1-routing-trillion-parameter-scaling/the-switch-layer2026-01-05T17:34:32.000Zhttps://mbrenndoerfer.com/writing/switch-transformer-top-1-routing-trillion-parameter-scaling/top-1-routing-the-simplification-insight2026-01-05T17:34:32.000Zhttps://mbrenndoerfer.com/writing/switch-transformer-top-1-routing-trillion-parameter-scaling/capacity-factor-managing-overflow2026-01-05T17:34:32.000Zhttps://mbrenndoerfer.com/writing/switch-transformer-top-1-routing-trillion-parameter-scaling/complete-switch-layer-implementation2026-01-05T17:34:32.000Zhttps://mbrenndoerfer.com/writing/switch-transformer-top-1-routing-trillion-parameter-scaling/key-parameters2026-01-05T17:34:32.000Zhttps://mbrenndoerfer.com/writing/switch-transformer-top-1-routing-trillion-parameter-scaling/training-stability-strategies2026-01-05T17:34:32.000Zhttps://mbrenndoerfer.com/writing/switch-transformer-top-1-routing-trillion-parameter-scaling/scaling-results2026-01-05T17:34:32.000Zhttps://mbrenndoerfer.com/writing/switch-transformer-top-1-routing-trillion-parameter-scaling/distillation-and-fine-tuning2026-01-05T17:34:32.000Zhttps://mbrenndoerfer.com/writing/switch-transformer-top-1-routing-trillion-parameter-scaling/worked-example-routing-visualization2026-01-05T17:34:32.000Zhttps://mbrenndoerfer.com/writing/switch-transformer-top-1-routing-trillion-parameter-scaling/worked-example-step-by-step-routing-trace2026-01-05T17:34:32.000Zhttps://mbrenndoerfer.com/writing/switch-transformer-top-1-routing-trillion-parameter-scaling/limitations-and-practical-considerations2026-01-05T17:34:32.000Zhttps://mbrenndoerfer.com/writing/switch-transformer-top-1-routing-trillion-parameter-scaling/summary2026-01-05T17:34:32.000Zhttps://mbrenndoerfer.com/writing/switch-transformer-top-1-routing-trillion-parameter-scaling/quiz2026-01-05T17:34:32.000Z