Update template name

adolfo-ab · adolfo-ab · commit 8625b4d6149e · 2025-03-26T10:29:30.000+01:00
diff --git a/tests/model_explainability/guardrails/conftest.py b/tests/model_explainability/guardrails/conftest.py
@@ -100,7 +100,7 @@ def vllm_runtime(
         client=admin_client,
         name="vllm-runtime-cpu-fp16",
         namespace=model_namespace.name,
-        template_name="vllm-cpu-runtime-template",
+        template_name="vllm-cuda-runtime-template",
         deployment_type=KServeDeploymentType.RAW_DEPLOYMENT,
         runtime_image="quay.io/rh-aiservices-bu/vllm-cpu-openai-ubi9"
         "@sha256:d680ff8becb6bbaf83dfee7b2d9b8a2beb130db7fd5aa7f9a6d8286a58cebbfd",
diff --git a/tests/model_serving/model_runtime/vllm/constant.py b/tests/model_serving/model_runtime/vllm/constant.py
@@ -7,7 +7,7 @@
 VLLM_SUPPORTED_QUANTIZATION: list[str] = ["marlin", "awq"]
 # Configurations
 TEMPLATE_MAP: dict[str, str] = {
-    AcceleratorType.NVIDIA: "vllm-runtime-template",
+    AcceleratorType.NVIDIA: "vllm-cuda-runtime-template",
     AcceleratorType.AMD: "vllm-rocm-runtime-template",
     AcceleratorType.GAUDI: "vllm-gaudi-runtime-template",
 }

Original file line number	Diff line number	Diff line change
`@@ -7,7 +7,7 @@`
`7`	`7`	`VLLM_SUPPORTED_QUANTIZATION: list[str] = ["marlin", "awq"]`
`8`	`8`	`# Configurations`
`9`	`9`	`TEMPLATE_MAP: dict[str, str] = {`
`10`		`- AcceleratorType.NVIDIA: "vllm-runtime-template",`
	`10`	`+ AcceleratorType.NVIDIA: "vllm-cuda-runtime-template",`
`11`	`11`	`AcceleratorType.AMD: "vllm-rocm-runtime-template",`
`12`	`12`	`AcceleratorType.GAUDI: "vllm-gaudi-runtime-template",`
`13`	`13`	`}`