|
Mila
Deep Neural Network Library
|
Files | |
| Gemma.Block.ixx | |
| Gemma 4 decoder block (inference: prefill + decode), one type per attention kind. | |
| Gemma.Config.ixx | |
| Network-level configuration for Gemma 4 transformer networks. | |
| Gemma.ixx | |
| Gemma 4 decoder-only transformer network (inference: prefill + decode). | |
| Gemma.Protocol.ixx | |
| Canonical Gemma 4 native token grammar: parse/format for the model's registered turn / channel / tool-call / tool-response vocabulary. | |
| IDecoderLayer.ixx | |
| Virtual inference interface for a heterogeneous decoder layer list. | |