Skip to content

test(serve): run the recommender integ tests on ml.g6 and ml.g7 instances #6557

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

Merged
papriwal merged 1 commit into from
Nov 4, 2026
Merged

test(serve): run the recommender integ tests on ml.g6 and ml.g7 instances #6557

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
13 changes: 9 additions & 4 deletions sagemaker-serve/tests/integ/test_ai_inference_recommender_integration.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,8 @@
# serves /v1/chat/completions, matching the OpenAI api_standard the
# synthetic Workload sends.
MODEL_ID = "huggingface-llm-qwen2-1-5b-instruct"
INSTANCE_TYPE = "ml.g5.2xlarge"
MODEL_INSTANCE_TYPE = "ml.g6.2xlarge"
RECOMMENDATION_INSTANCE_TYPE = "ml.g7.2xlarge"
WORKLOAD_TOKENIZER = "gpt2"
WORKLOAD_REQUEST_COUNT = 10
WORKLOAD_CONCURRENCY = 1
Expand All @@ -63,7 +64,7 @@ def _build_synthetic_workload():


def _build_jumpstart_model_builder(role_arn):
compute = Compute(instance_type=INSTANCE_TYPE)
compute = Compute(instance_type=MODEL_INSTANCE_TYPE)
jumpstart_config = JumpStartConfig(model_id=MODEL_ID)
return ModelBuilder.from_jumpstart_config(
jumpstart_config=jumpstart_config, compute=compute, role_arn=role_arn
Expand Down Expand Up @@ -152,7 +153,7 @@ def test_recommendation_workflow_end_to_end():
recommendation_job = model_builder.generate_deployment_recommendations(
workload=_build_synthetic_workload(),
performance_target="throughput",
instance_types=[INSTANCE_TYPE],
instance_types=[RECOMMENDATION_INSTANCE_TYPE],
Comment thread
ZealSV marked this conversation as resolved.
Resolved
advanced_optimization=False,
framework="LMI",
role_arn=role,
Expand Down Expand Up @@ -197,10 +198,14 @@ def test_recommendation_workflow_end_to_end():
wait=True,
)
logger.info(f"Recommendation endpoint deployed: {rec_endpoint.endpoint_name}")
rec_model = Model.get(model_name=rec_model_name)
assert (
rec_endpoint.endpoint_status == "InService"
), f"Endpoint did not reach InService: {rec_endpoint.endpoint_status}"
rec_model = Model.get(model_name=rec_model_name)
variants = EndpointConfig.get(
endpoint_config_name=rec_endpoint_config_name
).production_variants
assert [variant.instance_type for variant in variants] == [RECOMMENDATION_INSTANCE_TYPE]

finally:
if rec_endpoint and rec_model:
Expand Down
Loading