On: Transformer architecture optimized for Apple Silic...

[callen43]

Is there also something available to make use of the ANE during _training_? E.g fine-tuning BERT on an M1 Mac in a couple of hours?

(This here only applies to inference, right?)

[machinekob → callen43]

Its FP16/Int8 inference only (cause you can only access it via apple frameworks that dosent support training). Also its only used if your data is small enough (4mb cache) it wont be useful for big transformers/ big images processing in a while.