Hardcoded Triton Runtime Image in Triton testsuite (#853)

* Hardcoded triton image

* fixed ns name

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update TRITON_IMAGE version to 24.10-py3

* Changed image version

* added smoke marker

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Author: Raghul-M

tests/conftest.py

@@ -312,10 +312,12 @@ def mlserver_runtime_image(pytestconfig: pytest.Config) -> str | None:
 
 
 @pytest.fixture(scope="session")
-def triton_runtime_image(pytestconfig: pytest.Config) -> str | None:
+def triton_runtime_image(pytestconfig: pytest.Config) -> str:
+    from tests.model_serving.model_runtime.triton.constant import TRITON_IMAGE
+
     runtime_image = pytestconfig.option.triton_runtime_image
     if not runtime_image:
-        return None
+        return TRITON_IMAGE
     return runtime_image
 
 

tests/model_serving/model_runtime/triton/basic_model_deployment/test_pytorch_model.py

@@ -31,6 +31,7 @@
 )
 
 
+@pytest.mark.sanity
 @pytest.mark.parametrize(
     ("protocol", "model_namespace", "s3_models_storage_uri", "triton_serving_runtime", "triton_inference_service"),
     [

tests/model_serving/model_runtime/triton/constant.py

@@ -30,6 +30,10 @@
 TRITON_REST_PORT: int = 8080
 TRITON_GRPC_PORT: int = 9000
 
+
+TRITON_IMAGE: str = "nvcr.io/nvidia/tritonserver:24.10-py3"
+
+
 MODEL_PATH_PREFIX_KERAS: str = "triton_resnet/model_repository"
 MODEL_PATH_PREFIX: str = "triton/model_repository"
 MODEL_PATH_PREFIX_DALI: str = "triton_gpu/model_repository"

tests/model_serving/model_runtime/vllm/basic_model_deployment/test_granite_2b_instruct_preview_4k_r240917a.py

@@ -15,7 +15,7 @@
     "model_namespace, s3_models_storage_uri, serving_runtime, vllm_inference_service",
     [
         pytest.param(
-            {"name": "granite-serverless-raw"},
+            {"name": "granite-raw"},
             {"model-dir": "granite-2b-instruct-preview-4k-r240917a"},
             {"deployment_type": KServeDeploymentType.RAW_DEPLOYMENT},
             {