[Model] Add user-configurable task for models that support both generation and embedding (#9424)

docs/source/models/supported_models.rst

@@ -294,6 +294,10 @@ Text Embedding
     - 
     - ✅︎
 
+.. important::
+  Some model architectures support both generation and embedding tasks.
+  In this case, you have to pass :code:`--task embedding` to run the model in embedding mode.
+
 Reward Modeling
 ---------------
 
@@ -482,6 +486,10 @@ Multimodal Embedding
     - 🚧
     - ✅︎
 
+.. important::
+  Some model architectures support both generation and embedding tasks.
+  In this case, you have to pass :code:`--task embedding` to run the model in embedding mode.
+
 ----
 
 If your model uses one of the above model architectures, you can seamlessly run your model with vLLM.