(feat) Add synthetic_data_kit provider integration for synthetic_data_generation API

The synthetic_data_kit provider integration enables high-quality synthetic dataset
generation for fine-tuning LLMs. This commit sets up the initial provider
registration and fixes provider resolution to properly handle type casting and
imports, ensuring proper integration with llama-stack's provider system.

Implementation of the actual provider functionality will follow in a subsequent
commit.

Signed-off-by: Alina Ryan <aliryan@redhat.com>

llama_stack/providers/registry/synthetic_data_generation.py

@@ -0,0 +1,28 @@
+# 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.
+
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# SPDX-License-Identifier: MIT
+
+from llama_stack.providers.datatypes import Api, InlineProviderSpec, ProviderSpec
+
+
+def available_providers() -> list[ProviderSpec]:
+    return [
+        InlineProviderSpec(
+            api=Api.synthetic_data_generation,
+            provider_type="inline::synthetic_data_kit",
+            pip_packages=[
+                "synthetic-data-kit",
+                "vllm",
+                "pydantic",
+            ],
+            module="llama_stack.providers.inline.synthetic_data_generation.synthetic_data_kit_inline",
+            config_class="llama_stack.providers.inline.synthetic_data_generation.config.SyntheticDataKitConfig",
+        ),
+    ]