kill sample providers, update tests thanks Eric, then fix all configs

llama_stack/providers/inline/inference/vllm/config.py

@@ -4,6 +4,8 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
+from typing import Any, Dict
+
 from pydantic import BaseModel, Field
 
 from llama_stack.schema_utils import json_schema_type
@@ -40,7 +42,7 @@ class VLLMConfig(BaseModel):
     )
 
     @classmethod
-    def sample_run_config(cls):
+    def sample_run_config(cls, **kwargs: Any) -> Dict[str, Any]:
         return {
             "tensor_parallel_size": "${env.TENSOR_PARALLEL_SIZE:1}",
             "max_tokens": "${env.MAX_TOKENS:4096}",