Support Roberta embedding models (#9387)

Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Signed-off-by: Flavia Beo <flavia.beo@ibm.com>
Co-authored-by: Flavia Beo <flavia.beo@ibm.com>

vllm/model_executor/models/registry.py

@@ -94,6 +94,8 @@ _TEXT_GENERATION_MODELS = {
 _EMBEDDING_MODELS = {
     # [Text-only]
     "BertModel": ("bert", "BertEmbeddingModel"),
+    "RobertaModel": ("roberta", "RobertaEmbeddingModel"),
+    "XLMRobertaModel": ("roberta", "RobertaEmbeddingModel"),
     "DeciLMForCausalLM": ("decilm", "DeciLMForCausalLM"),
     "Gemma2Model": ("gemma2", "Gemma2EmbeddingModel"),
     "LlamaModel": ("llama", "LlamaEmbeddingModel"),