model registration in ollama and vllm check against the available models in the provider (#446)

tests:
pytest -v -s -m "ollama"
llama_stack/providers/tests/inference/test_text_inference.py

pytest -v -s -m vllm_remote
llama_stack/providers/tests/inference/test_text_inference.py --env
VLLM_URL="http://localhost:9798/v1"

---------

llama_stack/providers/tests/inference/test_model_registration.py

@@ -0,0 +1,35 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+import pytest
+
+# How to run this test:
+#
+# pytest -v -s llama_stack/providers/tests/inference/test_model_registration.py
+#   -m "meta_reference"
+#   --env TOGETHER_API_KEY=<your_api_key>
+
+
+class TestModelRegistration:
+    @pytest.mark.asyncio
+    async def test_register_unsupported_model(self, inference_stack):
+        _, models_impl = inference_stack
+
+        # Try to register a model that's too large for local inference
+        with pytest.raises(Exception) as exc_info:
+            await models_impl.register_model(
+                model_id="Llama3.1-70B-Instruct",
+            )
+
+    @pytest.mark.asyncio
+    async def test_register_nonexistent_model(self, inference_stack):
+        _, models_impl = inference_stack
+
+        # Try to register a non-existent model
+        with pytest.raises(Exception) as exc_info:
+            await models_impl.register_model(
+                model_id="Llama3-NonExistent-Model",
+            )