feat: add static embedding metadata to dynamic model listings for providers using OpenAIMixin

- remove auto-download of ollama embedding models
- add embedding model metadata to dynamic listing w/ unit test
- add support and tests for allowed_models
- removed inference provider models.py files where dynamic listing is enabled
- store embedding metadata in embedding_model_metadata field on inference providers
- make model_entries optional on ModelRegistryHelper and LiteLLMOpenAIMixin
- make OpenAIMixin a ModelRegistryHelper
- skip base64 embedding test for remote::ollama, always returns floats
- only use OpenAI client for ollama model listing
- remove unused build_model_entry function
- remove unused get_huggingface_repo function

llama_stack/providers/remote/inference/cerebras/cerebras.py

@@ -49,7 +49,6 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
 )
 
 from .config import CerebrasImplConfig
-from .models import MODEL_ENTRIES
 
 
 class CerebrasInferenceAdapter(
@@ -58,10 +57,6 @@ class CerebrasInferenceAdapter(
     Inference,
 ):
     def __init__(self, config: CerebrasImplConfig) -> None:
-        ModelRegistryHelper.__init__(
-            self,
-            model_entries=MODEL_ENTRIES,
-        )
         self.config = config
 
         # TODO: make this use provider data, etc. like other providers