Inference integ test passed on beta account (#140)

* baseline inference integration test for CLI and SDK, minor bug fix for inference cli, clear inference sdk notebook output

* update integ test in progress

* update cli code, notebook, integ and unit test to add list_pods and get_logs

* clean up merge header

* inference integ tests all passing in chait's account

* integ test passing on beta account

Author: mollyheamazon

test/integration_tests/cli/test_cli_jumpstart_inference.py

@@ -34,10 +34,8 @@ def test_js_create(runner, js_endpoint_name):
         "--namespace", NAMESPACE,
         "--version", VERSION,
         "--model-id", "deepseek-llm-r1-distill-qwen-1-5b",
-        "--model-version", "2.0.4",
-        "--instance-type", "ml.g5.8xlarge",
+        "--instance-type", "ml.g5.4xlarge",
         "--endpoint-name", js_endpoint_name,
-        "--tls-certificate-output-s3-uri", "s3://tls-bucket-inf1-beta2"
     ])
     assert result.exit_code == 0, result.output
 

test/integration_tests/sdk/test_sdk_jumpstart_inference.py

@@ -15,10 +15,8 @@
 REGION = "us-east-2"
 ENDPOINT_NAME = "js-sdk-integration"
 
-INSTANCE_TYPE = "ml.g5.8xlarge"
+INSTANCE_TYPE = "ml.g5.4xlarge"
 MODEL_ID = "deepseek-llm-r1-distill-qwen-1-5b"
-MODEL_VERSION = "2.0.4"
-TLS_S3_URI = "s3://tls-bucket-inf1-beta2"
 
 TIMEOUT_MINUTES = 15
 POLL_INTERVAL_SECONDS = 30
@@ -29,12 +27,11 @@ def sagemaker_client():
 
 @pytest.fixture(scope="module")
 def endpoint_obj():
-    model = Model(model_id=MODEL_ID, model_version=MODEL_VERSION)
+    model = Model(model_id=MODEL_ID)
     server = Server(instance_type=INSTANCE_TYPE)
     sm_endpoint = SageMakerEndpoint(name=ENDPOINT_NAME)
-    tls = TlsConfig(tls_certificate_output_s3_uri=TLS_S3_URI)
 
-    return HPJumpStartEndpoint(model=model, server=server, sage_maker_endpoint=sm_endpoint, tls_config=tls)
+    return HPJumpStartEndpoint(model=model, server=server, sage_maker_endpoint=sm_endpoint)
 
 def test_create_endpoint(endpoint_obj):
     endpoint_obj.create(namespace=NAMESPACE)