Skip to content

v2 test updates #5817

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
mohamedzeidan2021 wants to merge 2 commits into
base: master-v2
Choose a base branch
from
Open

v2 test updates #5817

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
18f2241
v2 test updates
May 1, 2026
7412b08
instance types update
May 1, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
42 changes: 4 additions & 38 deletions tests/conftest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -641,42 +641,17 @@ def cpu_instance_type(sagemaker_session, request):

@pytest.fixture(scope="session")
def gpu_instance_type(sagemaker_session, request):
region = sagemaker_session.boto_session.region_name
if region in NO_P3_REGIONS:
return "ml.p2.xlarge"
else:
return "ml.p3.2xlarge"
return "ml.g4dn.xlarge"


@pytest.fixture()
def gpu_pytorch_instance_type(sagemaker_session, request):
fw_version = None
for pytorch_version_fixture in [
"pytorch_inference_version",
"huggingface_training_pytorch_latest_version",
"huggingface_inference_pytorch_latest_version",
]:
if pytorch_version_fixture in request.fixturenames:
fw_version = request.getfixturevalue(pytorch_version_fixture)
if fw_version is None:
fw_version = request.param
region = sagemaker_session.boto_session.region_name
if region in NO_P3_REGIONS:
if Version(fw_version) >= Version("1.13"):
return PYTORCH_RENEWED_GPU
else:
return "ml.p2.xlarge"
else:
return "ml.p3.2xlarge"
return "ml.g4dn.xlarge"


@pytest.fixture(scope="session")
def gpu_instance_type_list(sagemaker_session, request):
region = sagemaker_session.boto_session.region_name
if region in NO_P3_REGIONS:
return ["ml.p2.xlarge"]
else:
return ["ml.p3.2xlarge", "ml.p2.xlarge"]
return ["ml.g4dn.xlarge"]


@pytest.fixture(scope="session")
Expand Down Expand Up @@ -717,16 +692,7 @@ def pytest_generate_tests(metafunc):
cpu_instance_type = "ml.m5.xlarge" if region in NO_M4_REGIONS else "ml.m4.xlarge"

params = [cpu_instance_type]
if not (
region in tests.integ.HOSTING_NO_P3_REGIONS
or region in tests.integ.TRAINING_NO_P3_REGIONS
):
params.append("ml.p3.2xlarge")
elif not (
region in tests.integ.HOSTING_NO_P2_REGIONS
or region in tests.integ.TRAINING_NO_P2_REGIONS
):
params.append("ml.p2.xlarge")
params.append("ml.g4dn.xlarge")

metafunc.parametrize("instance_type", params, scope="session")

Expand Down
Binary file added ...ark/code/java/hello-java-spark/com/amazonaws/sagemaker/spark/test/HelloJavaSparkApp.class
View file
Open in desktop
Binary file not shown.
Binary file added tests/data/spark/code/java/hello-java-spark/hello-spark-java.jar
View file
Open in desktop
Binary file not shown.
12 changes: 7 additions & 5 deletions tests/integ/sagemaker/jumpstart/model/test_jumpstart_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -95,9 +95,10 @@ def test_prepacked_jumpstart_model(setup):
sagemaker_session=get_sm_session(),
)

# uses ml.p3.2xlarge instance
# uses ml.g4dn.xlarge instance
predictor = model.deploy(
tags=[{"Key": JUMPSTART_TAG, "Value": os.environ[ENV_VAR_JUMPSTART_SDK_TEST_SUITE_ID]}],
instance_type="ml.g4dn.xlarge",
)

response = predictor.predict("hello world!")
Expand All @@ -120,7 +121,7 @@ def test_model_package_arn_jumpstart_model(setup):
sagemaker_session=get_sm_session(),
)

# uses ml.g5.2xlarge instance
# uses ml.g4dn.2xlarge instance
predictor = model.deploy(
tags=[{"Key": JUMPSTART_TAG, "Value": os.environ[ENV_VAR_JUMPSTART_SDK_TEST_SUITE_ID]}],
)
Expand Down Expand Up @@ -175,7 +176,7 @@ def test_jumpstart_gated_model(setup):
sagemaker_session=get_sm_session(),
)

# uses ml.g5.2xlarge instance
# uses ml.g4dn.2xlarge instance
predictor = model.deploy(
tags=[{"Key": JUMPSTART_TAG, "Value": os.environ[ENV_VAR_JUMPSTART_SDK_TEST_SUITE_ID]}],
accept_eula=True,
Expand Down Expand Up @@ -206,6 +207,7 @@ def test_jumpstart_gated_model_inference_component_enabled(setup):
tags=[{"Key": JUMPSTART_TAG, "Value": os.environ[ENV_VAR_JUMPSTART_SDK_TEST_SUITE_ID]}],
accept_eula=True,
endpoint_type=EndpointType.INFERENCE_COMPONENT_BASED,
instance_type="ml.g5.2xlarge",
)

predictor = retrieve_default(
Expand Down Expand Up @@ -262,7 +264,7 @@ def test_jumpstart_model_register(setup):

# uses instance
predictor = model_package.deploy(
instance_type="ml.p3.2xlarge",
instance_type="ml.g4dn.xlarge",
initial_instance_count=1,
)

Expand Down Expand Up @@ -379,7 +381,7 @@ def test_jumpstart_model_with_deployment_configs(setup):

model.set_deployment_config(
configs[0]["ConfigName"],
"ml.g5.2xlarge",
"ml.g4dn.2xlarge",
)
assert model.config_name == configs[0]["ConfigName"]

Expand Down
11 changes: 9 additions & 2 deletions ...s/integ/sagemaker/jumpstart/private_hub/estimator/test_jumpstart_private_hub_estimator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,6 +69,7 @@ def test_jumpstart_hub_estimator(setup, add_model_references):
model_id=model_id,
hub_name=os.environ[ENV_VAR_JUMPSTART_SDK_TEST_HUB_NAME],
tags=[{"Key": JUMPSTART_TAG, "Value": os.environ[ENV_VAR_JUMPSTART_SDK_TEST_SUITE_ID]}],
instance_type="ml.g4dn.xlarge",
)

estimator.fit(
Expand All @@ -85,9 +86,10 @@ def test_jumpstart_hub_estimator(setup, add_model_references):
model_version=model_version,
)

# uses ml.p3.2xlarge instance
# uses ml.g4dn.xlarge instance
predictor = estimator.deploy(
tags=[{"Key": JUMPSTART_TAG, "Value": os.environ[ENV_VAR_JUMPSTART_SDK_TEST_SUITE_ID]}],
instance_type="ml.g4dn.xlarge",
)

response = predictor.predict(["hello", "world"])
Expand All @@ -107,6 +109,7 @@ def test_jumpstart_hub_estimator_with_session(setup, add_model_references):
sagemaker_session=sagemaker_session,
tags=[{"Key": JUMPSTART_TAG, "Value": os.environ[ENV_VAR_JUMPSTART_SDK_TEST_SUITE_ID]}],
hub_name=os.environ[ENV_VAR_JUMPSTART_SDK_TEST_HUB_NAME],
instance_type="ml.g4dn.xlarge",
)

estimator.fit(
Expand All @@ -124,11 +127,12 @@ def test_jumpstart_hub_estimator_with_session(setup, add_model_references):
sagemaker_session=get_sm_session(),
)

# uses ml.p3.2xlarge instance
# uses ml.g4dn.xlarge instance
predictor = estimator.deploy(
tags=[{"Key": JUMPSTART_TAG, "Value": os.environ[ENV_VAR_JUMPSTART_SDK_TEST_SUITE_ID]}],
role=get_sm_session().get_caller_identity_arn(),
sagemaker_session=get_sm_session(),
instance_type="ml.g4dn.xlarge",
)

response = predictor.predict(["hello", "world"])
Expand All @@ -144,6 +148,7 @@ def test_jumpstart_hub_gated_estimator_with_eula(setup, add_model_references):
model_id=model_id,
hub_name=os.environ[ENV_VAR_JUMPSTART_SDK_TEST_HUB_NAME],
tags=[{"Key": JUMPSTART_TAG, "Value": os.environ[ENV_VAR_JUMPSTART_SDK_TEST_SUITE_ID]}],
instance_type="ml.g5.2xlarge",
)

estimator.fit(
Expand All @@ -158,6 +163,7 @@ def test_jumpstart_hub_gated_estimator_with_eula(setup, add_model_references):
tags=[{"Key": JUMPSTART_TAG, "Value": os.environ[ENV_VAR_JUMPSTART_SDK_TEST_SUITE_ID]}],
role=get_sm_session().get_caller_identity_arn(),
sagemaker_session=get_sm_session(),
instance_type="ml.g5.2xlarge",
)

payload = {
Expand All @@ -178,6 +184,7 @@ def test_jumpstart_hub_gated_estimator_without_eula(setup, add_model_references)
model_id=model_id,
hub_name=os.environ[ENV_VAR_JUMPSTART_SDK_TEST_HUB_NAME],
tags=[{"Key": JUMPSTART_TAG, "Value": os.environ[ENV_VAR_JUMPSTART_SDK_TEST_SUITE_ID]}],
instance_type="ml.g5.2xlarge",
)
with pytest.raises(Exception):
estimator.fit(
Expand Down
1 change: 1 addition & 0 deletions tests/integ/sagemaker/jumpstart/private_hub/model/test_jumpstart_private_hub_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,6 +116,7 @@ def test_jumpstart_hub_gated_model(setup, add_model_references):
predictor = model.deploy(
accept_eula=True,
tags=[{"Key": JUMPSTART_TAG, "Value": os.environ[ENV_VAR_JUMPSTART_SDK_TEST_SUITE_ID]}],
instance_type="ml.g5.2xlarge",
)

payload = model.retrieve_example_payload()
Expand Down
4 changes: 2 additions & 2 deletions tests/integ/sagemaker/jumpstart/retrieve_uri/test_transfer_learning.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,8 +34,8 @@
def test_jumpstart_transfer_learning_retrieve_functions(setup):

model_id, model_version = "huggingface-spc-bert-base-cased", "2.0.3"
training_instance_type = "ml.p3.2xlarge"
inference_instance_type = "ml.p2.xlarge"
training_instance_type = "ml.g4dn.xlarge"
inference_instance_type = "ml.g4dn.xlarge"

# training
print("Starting training...")
Expand Down
8 changes: 2 additions & 6 deletions tests/integ/sagemaker/jumpstart/script_mode_class/test_transfer_learning.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,12 +53,8 @@ def test_jumpstart_transfer_learning_estimator_class(setup):

model_id, model_version = "huggingface-spc-bert-base-cased", "1.2.3"

inference_instance_type = instance_types.retrieve_default(
model_id=model_id, model_version=model_version, scope="inference"
)
training_instance_type = instance_types.retrieve_default(
model_id=model_id, model_version=model_version, scope="training"
)
inference_instance_type = "ml.g4dn.xlarge"
training_instance_type = "ml.g4dn.xlarge"
instance_count = 1

print("Starting training...")
Expand Down
10 changes: 5 additions & 5 deletions tests/integ/test_training_compiler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@

@pytest.fixture(scope="module")
def gpu_instance_type(request):
return "ml.p3.2xlarge"
return "ml.g4dn.xlarge"


@pytest.fixture(scope="module")
Expand Down Expand Up @@ -86,8 +86,8 @@ def skip_if_incompatible(gpu_instance_type, request):
@pytest.mark.parametrize(
"gpu_instance_type,instance_count",
[
pytest.param("ml.p3.2xlarge", 1, marks=pytest.mark.release),
pytest.param("ml.p3.16xlarge", 2),
pytest.param("ml.g4dn.xlarge", 1, marks=pytest.mark.release),
pytest.param("ml.g4dn.12xlarge", 2),
],
)
@pytest.mark.skipif(
Expand Down Expand Up @@ -138,8 +138,8 @@ def test_huggingface_pytorch(
@pytest.mark.parametrize(
"gpu_instance_type,instance_count",
[
pytest.param("ml.p3.2xlarge", 1, marks=pytest.mark.release),
pytest.param("ml.p3.16xlarge", 2),
pytest.param("ml.g4dn.xlarge", 1, marks=pytest.mark.release),
pytest.param("ml.g4dn.12xlarge", 2),
],
)
@pytest.mark.skip("Temporarily skip to unblock")
Expand Down
Loading