workers

# What does this PR do?


## Test Plan

src/llama_stack/cli/stack/run.py

@@ -127,7 +127,7 @@ class StackRun(Subcommand):
             config = StackRunConfig(**cast_image_name_to_string(replace_env_vars(config_contents)))
 
         port = args.port or config.server.port
-        host = config.server.host or ["::", "0.0.0.0"]
+        host = config.server.host or "0.0.0.0"
 
         # Set the config file in environment so create_app can find it
         os.environ["LLAMA_STACK_CONFIG"] = str(config_file)
@@ -139,6 +139,7 @@ class StackRun(Subcommand):
             "lifespan": "on",
             "log_level": logger.getEffectiveLevel(),
             "log_config": logger_config,
+            "workers": config.server.workers,
         }
 
         keyfile = config.server.tls_keyfile

src/llama_stack/core/datatypes.py

@@ -473,6 +473,10 @@ class ServerConfig(BaseModel):
         "- true: Enable localhost CORS for development\n"
         "- {allow_origins: [...], allow_methods: [...], ...}: Full configuration",
     )
+    workers: int = Field(
+        default=1,
+        description="Number of workers to use for the server",
+    )
 
 
 class StackRunConfig(BaseModel):