Unable to scale in instances group instance_count to 0 #347
Description
When I set instance_count to 0
cluster_name="hyp-cluster"
hyp update cluster --cluster-name $cluster_name \
--instance-groups '[{
"instance_group_name": "xxx",
"instance_type": "ml.g5.2xlarge",
"instance_count": 0,
"execution_role": "arn:aws:iam::123456789012:role/hyp-clusterExecRole",
"life_cycle_config": {
"source_s3_uri": "s3://hyp-bucket",
"on_create": "on_create.sh"
}
}]'
Error message as following
INFO:sagemaker_core.main.resources:Updating cluster resource.
╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮
│ /Users/qruwang/pyenv/base/bin/hyp:7 in <module> │
│ │
│ 4 if __name__ == '__main__': │
│ 5 │ if sys.argv[0].endswith('.exe'): │
│ 6 │ │ sys.argv[0] = sys.argv[0][:-4] │
│ ❱ 7 │ sys.exit(cli()) │
│ 8 │
│ │
│ /Users/qruwang/pyenv/base/lib/python3.13/site-packages/click/core.py:1157 in __call__ │
│ │
│ 1154 │ │
│ 1155 │ def __call__(self, *args: t.Any, **kwargs: t.Any) -> t.Any: │
│ 1156 │ │ """Alias for :meth:`main`.""" │
│ ❱ 1157 │ │ return self.main(*args, **kwargs) │
│ 1158 │
│ 1159 │
│ 1160 class Command(BaseCommand): │
│ │
│ /Users/qruwang/pyenv/base/lib/python3.13/site-packages/click/core.py:1078 in main │
│ │
│ 1075 │ │ try: │
│ 1076 │ │ │ try: │
│ 1077 │ │ │ │ with self.make_context(prog_name, args, **extra) as ctx: │
│ ❱ 1078 │ │ │ │ │ rv = self.invoke(ctx) │
│ 1079 │ │ │ │ │ if not standalone_mode: │
│ 1080 │ │ │ │ │ │ return rv │
│ 1081 │ │ │ │ │ # it's not safe to `ctx.exit(rv)` here! │
│ │
│ /Users/qruwang/pyenv/base/lib/python3.13/site-packages/click/core.py:1688 in invoke │
│ │
│ 1685 │ │ │ │ super().invoke(ctx) │
│ 1686 │ │ │ │ sub_ctx = cmd.make_context(cmd_name, args, parent=ctx) │
│ 1687 │ │ │ │ with sub_ctx: │
│ ❱ 1688 │ │ │ │ │ return _process_result(sub_ctx.command.invoke(sub_ctx)) │
│ 1689 │ │ │
│ 1690 │ │ # In chain mode we create the contexts step by step, but after the │
│ 1691 │ │ # base command has been invoked. Because at that point we do not │
│ │
│ /Users/qruwang/pyenv/base/lib/python3.13/site-packages/click/core.py:1688 in invoke │
│ │
│ 1685 │ │ │ │ super().invoke(ctx) │
│ 1686 │ │ │ │ sub_ctx = cmd.make_context(cmd_name, args, parent=ctx) │
│ 1687 │ │ │ │ with sub_ctx: │
│ ❱ 1688 │ │ │ │ │ return _process_result(sub_ctx.command.invoke(sub_ctx)) │
│ 1689 │ │ │
│ 1690 │ │ # In chain mode we create the contexts step by step, but after the │
│ 1691 │ │ # base command has been invoked. Because at that point we do not │
│ │
│ /Users/qruwang/pyenv/base/lib/python3.13/site-packages/click/core.py:1434 in invoke │
│ │
│ 1431 │ │ │ echo(style(message, fg="red"), err=True) │
│ 1432 │ │ │
│ 1433 │ │ if self.callback is not None: │
│ ❱ 1434 │ │ │ return ctx.invoke(self.callback, **ctx.params) │
│ 1435 │ │
│ 1436 │ def shell_complete(self, ctx: Context, incomplete: str) -> t.List["CompletionItem"]: │
│ 1437 │ │ """Return a list of completions for the incomplete value. Looks │
│ │
│ /Users/qruwang/pyenv/base/lib/python3.13/site-packages/click/core.py:783 in invoke │
│ │
│ 780 │ │ │
│ 781 │ │ with augment_usage_errors(__self): │
│ 782 │ │ │ with ctx: │
│ ❱ 783 │ │ │ │ return __callback(*args, **kwargs) │
│ 784 │ │
│ 785 │ def forward( │
│ 786 │ │ __self, __cmd: "Command", *args: t.Any, **kwargs: t.Any # noqa: B902 │
│ │
│ /Users/qruwang/pyenv/base/lib/python3.13/site-packages/sagemaker/hyperpod/common/telemetry/telem │
│ etry_logging.py:179 in wrapper │
│ │
│ 176 │ │ │ │
│ 177 │ │ │ start = perf_counter() │
│ 178 │ │ │ try: │
│ ❱ 179 │ │ │ │ result = func(*args, **kwargs) │
│ 180 │ │ │ │ duration = round(perf_counter() - start, 2) │
│ 181 │ │ │ │ extra += f"&x-latency={duration}" │
│ 182 │ │ │ │ _send_telemetry_request( │
│ │
│ /Users/qruwang/pyenv/base/lib/python3.13/site-packages/sagemaker/hyperpod/cli/commands/cluster_s │
│ tack.py:389 in update_cluster │
│ │
│ 386 │ │ update_params['node_recovery'] = node_recovery │
│ 387 │ │
│ 388 │ click.secho(f"Update Params: {update_params}") │
│ ❱ 389 │ cluster.update(**update_params) │
│ 390 │ │
│ 391 │ logger.info("Cluster has been updated") │
│ 392 │ click.secho(f"Cluster {cluster_name} has been updated") │
│ │
│ /Users/qruwang/pyenv/base/lib/python3.13/site-packages/sagemaker_core/main/resources.py:3278 in │
│ wrapper │
│ │
│ 3275 │ │ │ │ }, │
│ 3276 │ │ │ │ "cluster_role": {"type": "string"}, │
│ 3277 │ │ │ } │
│ ❱ 3278 │ │ │ return create_func( │
│ 3279 │ │ │ │ *args, │
│ 3280 │ │ │ │ **Base.get_updated_kwargs_with_configured_attributes( │
│ 3281 │ │ │ │ │ config_schema_for_resource, "Cluster", **kwargs │
│ │
│ /Users/qruwang/pyenv/base/lib/python3.13/site-packages/sagemaker_core/main/resources.py:140 in │
│ wrapper │
│ │
│ 137 │ │ @functools.wraps(func) │
│ 138 │ │ def wrapper(*args, **kwargs): │
│ 139 │ │ │ config = dict(arbitrary_types_allowed=True) │
│ ❱ 140 │ │ │ return validate_call(config=config)(func)(*args, **kwargs) │
│ 141 │ │ │
│ 142 │ │ return wrapper │
│ 143 │
│ │
│ /Users/qruwang/pyenv/base/lib/python3.13/site-packages/pydantic/_internal/_validate_call.py:39 │
│ in wrapper_function │
│ │
│ 36 │ │ │
│ 37 │ │ @functools.wraps(wrapped) │
│ 38 │ │ def wrapper_function(*args, **kwargs): │
│ ❱ 39 │ │ │ return wrapper(*args, **kwargs) │
│ 40 │ │
│ 41 │ # We need to manually update this because `partial` object has no `__name__` and `__ │
│ 42 │ wrapper_function.__name__ = extract_function_name(wrapped) │
│ │
│ /Users/qruwang/pyenv/base/lib/python3.13/site-packages/pydantic/_internal/_validate_call.py:136 │
│ in __call__ │
│ │
│ 133 │ │ if not self.__pydantic_complete__: │
│ 134 │ │ │ self._create_validators() │
│ 135 │ │ │
│ ❱ 136 │ │ res = self.__pydantic_validator__.validate_python(pydantic_core.ArgsKwargs(args, │
│ 137 │ │ if self.__return_pydantic_validator__: │
│ 138 │ │ │ return self.__return_pydantic_validator__(res) │
│ 139 │ │ else: │
│ │
│ /Users/qruwang/pyenv/base/lib/python3.13/site-packages/sagemaker_core/main/resources.py:3527 in │
│ update │
│ │
│ 3524 │ │ logger.debug(f"Serialized input request: {operation_input_args}") │
│ 3525 │ │ │
│ 3526 │ │ # create the resource │
│ ❱ 3527 │ │ response = client.update_cluster(**operation_input_args) │
│ 3528 │ │ logger.debug(f"Response: {response}") │
│ 3529 │ │ self.refresh() │
│ 3530 │
│ │
│ /Users/qruwang/pyenv/base/lib/python3.13/site-packages/botocore/client.py:602 in _api_call │
│ │
│ 599 │ │ │ │ │ f"{py_operation_name}() only accepts keyword arguments." │
│ 600 │ │ │ │ ) │
│ 601 │ │ │ # The "self" in this scope is referring to the BaseClient. │
│ ❱ 602 │ │ │ return self._make_api_call(operation_name, kwargs) │
│ 603 │ │ │
│ 604 │ │ _api_call.__name__ = str(py_operation_name) │
│ 605 │
│ │
│ /Users/qruwang/pyenv/base/lib/python3.13/site-packages/botocore/context.py:123 in wrapper │
│ │
│ 120 │ │ │ with start_as_current_context(): │
│ 121 │ │ │ │ if hook: │
│ 122 │ │ │ │ │ hook() │
│ ❱ 123 │ │ │ │ return func(*args, **kwargs) │
│ 124 │ │ │
│ 125 │ │ return wrapper │
│ 126 │
│ │
│ /Users/qruwang/pyenv/base/lib/python3.13/site-packages/botocore/client.py:1035 in _make_api_call │
│ │
│ 1032 │ │ │ # Pass arbitrary endpoint info with the Request │
│ 1033 │ │ │ # for use during construction. │
│ 1034 │ │ │ request_context['endpoint_properties'] = properties │
│ ❱ 1035 │ │ request_dict = self._convert_to_request_dict( │
│ 1036 │ │ │ api_params=api_params, │
│ 1037 │ │ │ operation_model=operation_model, │
│ 1038 │ │ │ endpoint_url=endpoint_url, │
│ │
│ /Users/qruwang/pyenv/base/lib/python3.13/site-packages/botocore/client.py:1102 in │
│ _convert_to_request_dict │
│ │
│ 1099 │ │ headers=None, │
│ 1100 │ │ set_user_agent_header=True, │
│ 1101 │ ): │
│ ❱ 1102 │ │ request_dict = self._serializer.serialize_to_request( │
│ 1103 │ │ │ api_params, operation_model │
│ 1104 │ │ ) │
│ 1105 │ │ if not self._client_config.inject_host_prefix: │
│ │
│ /Users/qruwang/pyenv/base/lib/python3.13/site-packages/botocore/validate.py:381 in │
│ serialize_to_request │
│ │
│ 378 │ │ │ │ parameters, operation_model.input_shape │
│ 379 │ │ │ ) │
│ 380 │ │ │ if report.has_errors(): │
│ ❱ 381 │ │ │ │ raise ParamValidationError(report=report.generate_report()) │
│ 382 │ │ return self._serializer.serialize_to_request( │
│ 383 │ │ │ parameters, operation_model │
│ 384 │ │ ) │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
ParamValidationError: Parameter validation failed:
Missing required parameter in InstanceGroups[0]: "InstanceCount"
I can only set instance_count on console