* Add initial support for modeling_xlm encoder on NPU * Add EmbeddingModel class to keep the same usage with bce and npu fp16 linear convert * Optimize currently implementation to support EmbeddingModel.encode API and convert other torch modules to NPU * Add related example and documents |
||
|---|---|---|
| .. | ||
| CPU | ||
| GPU | ||
| NPU/HF-Transformers-AutoModels | ||