DLTS integration (#1945)

* skeleton of dlts training service (#1844)

* Hello, DLTS!

* Revert version

* Remove fs-extra

* Add some default cluster config

* schema

* fix

* Optional cluster (default to `.default`)

Depends on DLWorkspace#837

* fix

* fix

* optimize gpu type

* No more copy

* Format

* Code clean up

* Issue fix

* Add optional fields in config

* Issue fix

* Lint

* Lint

* Validate email, password and team

* Doc

* Doc fix

* Set TMPDIR

* Use metadata instead of gpu_capacity

* Cancel paused DLTS job

* workaround lint rules

* pylint

* doc
Co-authored-by: QuanluZhang <z.quanluzhang@gmail.com>

tools/nni_cmd/launcher_utils.py

@@ -5,8 +5,9 @@ import os
 import json
 from schema import SchemaError
 from schema import Schema
-from .config_schema import LOCAL_CONFIG_SCHEMA, REMOTE_CONFIG_SCHEMA, PAI_CONFIG_SCHEMA, PAI_YARN_CONFIG_SCHEMA, KUBEFLOW_CONFIG_SCHEMA,\
-                           FRAMEWORKCONTROLLER_CONFIG_SCHEMA, tuner_schema_dict, advisor_schema_dict, assessor_schema_dict
+from .config_schema import LOCAL_CONFIG_SCHEMA, REMOTE_CONFIG_SCHEMA, PAI_CONFIG_SCHEMA, PAI_YARN_CONFIG_SCHEMA, \
+                           DLTS_CONFIG_SCHEMA, KUBEFLOW_CONFIG_SCHEMA, FRAMEWORKCONTROLLER_CONFIG_SCHEMA, \
+                           tuner_schema_dict, advisor_schema_dict, assessor_schema_dict
 from .common_utils import print_error, print_warning, print_normal, get_yml_content
 
 def expand_path(experiment_config, key):
@@ -147,7 +148,9 @@ def validate_kubeflow_operators(experiment_config):
 def validate_common_content(experiment_config):
     '''Validate whether the common values in experiment_config is valid'''
     if not experiment_config.get('trainingServicePlatform') or \
-        experiment_config.get('trainingServicePlatform') not in ['local', 'remote', 'pai', 'kubeflow', 'frameworkcontroller', 'paiYarn']:
+        experiment_config.get('trainingServicePlatform') not in [
+                'local', 'remote', 'pai', 'kubeflow', 'frameworkcontroller', 'paiYarn', 'dlts'
+        ]:
         print_error('Please set correct trainingServicePlatform!')
         exit(1)
     schema_dict = {
@@ -156,7 +159,8 @@ def validate_common_content(experiment_config):
         'pai': PAI_CONFIG_SCHEMA,
         'paiYarn': PAI_YARN_CONFIG_SCHEMA,
         'kubeflow': KUBEFLOW_CONFIG_SCHEMA,
-        'frameworkcontroller': FRAMEWORKCONTROLLER_CONFIG_SCHEMA
+        'frameworkcontroller': FRAMEWORKCONTROLLER_CONFIG_SCHEMA,
+        'dlts': DLTS_CONFIG_SCHEMA,
         }
     separate_schema_dict = {
         'tuner': tuner_schema_dict,