|
Mila
Deep Neural Network Library
|
Classes | |
| class | Mila::Dnn::GemmaTransformer< TDeviceType, TPrecision, TWeightQuantization, TKvCachePolicy > |
| Gemma 4 transformer (decoder-only) for autoregressive inference. More... | |
Files | |
| file | Mila/Src/Dnn/Components/Transformers/Gemma/Gemma.ixx |
| Gemma 4 decoder-only transformer network (inference: prefill + decode). | |