chore(misc): update datasets, benchmarks to use alpha, beta prefixes (#3891)

This will be landed together with
https://github.com/llamastack/llama-stack-client-python/pull/282 (hence
CI will be red on this one.)

I have verified locally that tests pass with the updated version of the
client-sdk.

llama_stack/core/server/server.py

@@ -174,7 +174,9 @@ class StackApp(FastAPI):
 
 @asynccontextmanager
 async def lifespan(app: StackApp):
-    logger.info("Starting up")
+    server_version = parse_version("llama-stack")
+
+    logger.info(f"Starting up Llama Stack server (version: {server_version})")
     assert app.stack is not None
     app.stack.create_registry_refresh_task()
     yield