refactor: remove dead inference API code and clean up imports (#4093)

# What does this PR do?

Delete ~2,000 lines of dead code from the old bespoke inference API that
was replaced by OpenAI-only API. This includes removing unused type
conversion functions, dead provider methods, and event_logger.py.

Clean up imports across the codebase to remove references to deleted
types. This eliminates unnecessary
code and dependencies, helping isolate the API package as a
self-contained module.

This is the last interdependency between the .api package and "exterior"
packages, meaning that now every other package in llama stack imports
the API, not the other way around.

## Test Plan

this is a structural change, no tests needed.

---------

Signed-off-by: Charlie Doern <cdoern@redhat.com>

tests/unit/providers/inline/inference/__init__.py

@@ -0,0 +1,5 @@
+# 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.

tests/unit/providers/inline/inference/test_meta_reference.py

@@ -0,0 +1,44 @@
+# 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.
+
+from unittest.mock import Mock
+
+import pytest
+
+from llama_stack.providers.inline.inference.meta_reference.model_parallel import (
+    ModelRunner,
+)
+
+
+class TestModelRunner:
+    """Test ModelRunner task dispatching for model-parallel inference."""
+
+    def test_chat_completion_task_dispatch(self):
+        """Verify ModelRunner correctly dispatches chat_completion tasks."""
+        # Create a mock generator
+        mock_generator = Mock()
+        mock_generator.chat_completion = Mock(return_value=iter([]))
+
+        runner = ModelRunner(mock_generator)
+
+        # Create a chat_completion task
+        fake_params = {"model": "test"}
+        fake_messages = [{"role": "user", "content": "test"}]
+        task = ("chat_completion", [fake_params, fake_messages])
+
+        # Execute task
+        runner(task)
+
+        # Verify chat_completion was called with correct arguments
+        mock_generator.chat_completion.assert_called_once_with(fake_params, fake_messages)
+
+    def test_invalid_task_type_raises_error(self):
+        """Verify ModelRunner rejects invalid task types."""
+        mock_generator = Mock()
+        runner = ModelRunner(mock_generator)
+
+        with pytest.raises(ValueError, match="Unexpected task type"):
+            runner(("invalid_task", []))