Transformer can be converted into Mamba: Apple uses cross-architecture distillation to make inference cost linear

Transformer可以改装成Mamba了：苹果把推理成本直接打成线性

Apple presents a two-stage cross-architecture distillation path that converts Pythia-1B Transformer into a 1B HedgeMamba, reaching 14.11 perplexity with 10B tokens, about 2.7% of the teacher data. The teacher scores 13.86 PPL, while direct Transformer-to-Mamba distillation jumps above 100; the method first aligns with Hedgehog linear attention, then maps into Mamba initialization and fine-tunes. The key point is the path, not one trick: long-context inference shifts from quadratic to linear cost, and the post says downstream results on ARC, PIQA, BoolQ, RACE, and LogiQA approach the teacher.