Skip to content

Commit 57f5dc0

Browse files
fixing bug in ovms_kserve_inference_service function that was preventing isvcs from being created with 0 min-replicas
Signed-off-by: Brett Thompson <196701379+brettmthompson@users.noreply.github.com>
1 parent 2661c4a commit 57f5dc0

File tree

2 files changed

+6
-4
lines changed

2 files changed

+6
-4
lines changed

tests/model_serving/model_server/conftest.py

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -368,16 +368,18 @@ def ovms_kserve_inference_service(
368368
if env_vars := request.param.get("env-vars"):
369369
isvc_kwargs["model_env_variables"] = env_vars
370370

371-
if min_replicas := request.param.get("min-replicas"):
371+
if (min_replicas := request.param.get("min-replicas")) is not None:
372372
isvc_kwargs["min_replicas"] = min_replicas
373+
if min_replicas == 0:
374+
isvc_kwargs["wait_for_predictor_pods"] = False
373375

374376
if max_replicas := request.param.get("max-replicas"):
375377
isvc_kwargs["max_replicas"] = max_replicas
376378

377379
if scale_metric := request.param.get("scale-metric"):
378380
isvc_kwargs["scale_metric"] = scale_metric
379381

380-
if scale_target := request.param.get("scale-target"):
382+
if (scale_target := request.param.get("scale-target")) is not None:
381383
isvc_kwargs["scale_target"] = scale_target
382384

383385
with create_isvc(**isvc_kwargs) as isvc:

tests/model_serving/model_server/serverless/test_zero_initial_scale.py

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -52,7 +52,7 @@ def test_no_serverless_replicas_created_for_zero_initial_scale(
5252
"serving.knative.dev/configurationGeneration=1",
5353
create_isvc_label_selector_str(
5454
isvc=ovms_kserve_inference_service,
55-
resource_type="depoyment",
55+
resource_type="deployment",
5656
runtime_name=ovms_kserve_serving_runtime.name,
5757
),
5858
]
@@ -69,7 +69,7 @@ def test_no_serverless_replicas_created_for_zero_initial_scale(
6969
)
7070

7171
if deployments[0].instance.spec.replicas == 0:
72-
deployments[0].wait_for_replicas()
72+
deployments[0].wait_for_replicas(deployed=False)
7373
return
7474

7575
raise DeploymentValidationError(

0 commit comments

Comments
 (0)