feat: add provider data keys for Cerebras, Databricks, NVIDIA, and RunPod

- added missing tests for Fireworks, Anthropic, Gemini, SambaNova, and vLLM

llama_stack/providers/remote/inference/nvidia/nvidia.py

@@ -24,6 +24,8 @@ logger = get_logger(name=__name__, category="inference::nvidia")
 class NVIDIAInferenceAdapter(OpenAIMixin):
     config: NVIDIAConfig
 
+    provider_data_api_key_field: str = "nvidia_api_key"
+
     """
     NVIDIA Inference Adapter for Llama Stack.