def test_deployment_config_update(self):
b = DeploymentConfig(num_replicas=1, max_concurrent_queries=1)
# Test updating a key works.
b.num_replicas = 2
assert b.num_replicas == 2
# Check that not specifying a key doesn't update it.
assert b.max_concurrent_queries == 1
# Check that input is validated.
with pytest.raises(ValidationError):
b.num_replicas = "Hello"
with pytest.raises(ValidationError):
b.num_replicas = -1
def deployment(
_func_or_class: Optional[Callable] = None,
name: Optional[str] = None,
version: Optional[str] = None,
prev_version: Optional[str] = None,
num_replicas: Optional[int] = None,
init_args: Optional[Tuple[Any]] = None,
init_kwargs: Optional[Dict[Any, Any]] = None,
route_prefix: Union[str, None, DEFAULT] = DEFAULT.VALUE,
ray_actor_options: Optional[Dict] = None,
user_config: Optional[Any] = None,
max_concurrent_queries: Optional[int] = None,
_autoscaling_config: Optional[Union[Dict, AutoscalingConfig]] = None,
_graceful_shutdown_wait_loop_s: Optional[float] = None,
_graceful_shutdown_timeout_s: Optional[float] = None
) -> Callable[[Callable], Deployment]:
"""Define a Serve deployment.
Args:
name (Optional[str]): Globally-unique name identifying this deployment.
If not provided, the name of the class or function will be used.
version (Optional[str]): Version of the deployment. This is used to
indicate a code change for the deployment; when it is re-deployed
with a version change, a rolling update of the replicas will be
performed. If not provided, every deployment will be treated as a
new version.
prev_version (Optional[str]): Version of the existing deployment which
is used as a precondition for the next deployment. If prev_version
does not match with the existing deployment's version, the
deployment will fail. If not provided, deployment procedure will
not check the existing deployment's version.
num_replicas (Optional[int]): The number of processes to start up that
will handle requests to this deployment. Defaults to 1.
init_args (Optional[Tuple]): Positional args to be passed to the class
constructor when starting up deployment replicas. These can also be
passed when you call `.deploy()` on the returned Deployment.
init_kwargs (Optional[Dict]): Keyword args to be passed to the class
constructor when starting up deployment replicas. These can also be
passed when you call `.deploy()` on the returned Deployment.
route_prefix (Optional[str]): Requests to paths under this HTTP path
prefix will be routed to this deployment. Defaults to '/{name}'.
When set to 'None', no HTTP endpoint will be created.
Routing is done based on longest-prefix match, so if you have
deployment A with a prefix of '/a' and deployment B with a prefix
of '/a/b', requests to '/a', '/a/', and '/a/c' go to A and requests
to '/a/b', '/a/b/', and '/a/b/c' go to B. Routes must not end with
a '/' unless they're the root (just '/'), which acts as a
catch-all.
ray_actor_options (dict): Options to be passed to the Ray actor
constructor such as resource requirements.
user_config (Optional[Any]): [experimental] Config to pass to the
reconfigure method of the deployment. This can be updated
dynamically without changing the version of the deployment and
restarting its replicas. The user_config needs to be hashable to
keep track of updates, so it must only contain hashable types, or
hashable types nested in lists and dictionaries.
max_concurrent_queries (Optional[int]): The maximum number of queries
that will be sent to a replica of this deployment without receiving
a response. Defaults to 100.
Example:
>>> @serve.deployment(name="deployment1", version="v1")
class MyDeployment:
pass
>>> MyDeployment.deploy(*init_args)
>>> MyDeployment.options(num_replicas=2, init_args=init_args).deploy()
Returns:
Deployment
"""
if num_replicas is not None \
and _autoscaling_config is not None:
raise ValueError("Manually setting num_replicas is not allowed when "
"_autoscaling_config is provided.")
config = DeploymentConfig()
if num_replicas is not None:
config.num_replicas = num_replicas
if user_config is not None:
config.user_config = user_config
if max_concurrent_queries is not None:
config.max_concurrent_queries = max_concurrent_queries
if _autoscaling_config is not None:
config.autoscaling_config = _autoscaling_config
if _graceful_shutdown_wait_loop_s is not None:
config.graceful_shutdown_wait_loop_s = _graceful_shutdown_wait_loop_s
if _graceful_shutdown_timeout_s is not None:
config.graceful_shutdown_timeout_s = _graceful_shutdown_timeout_s
def decorator(_func_or_class):
return Deployment(
_func_or_class,
name if name is not None else _func_or_class.__name__,
config,
version=version,
prev_version=prev_version,
init_args=init_args,
init_kwargs=init_kwargs,
route_prefix=route_prefix,
ray_actor_options=ray_actor_options,
_internal=True,
)
# This handles both parametrized and non-parametrized usage of the
# decorator. See the @serve.batch code for more details.
return decorator(_func_or_class) if callable(_func_or_class) else decorator
