Add EKS test for vLLM

dlc_developer_config.toml

@@ -37,16 +37,16 @@ deep_canary_mode = false
 [build]
 # Add in frameworks you would like to build. By default, builds are disabled unless you specify building an image.
 # available frameworks - ["base", "vllm", "autogluon", "huggingface_tensorflow", "huggingface_pytorch", "huggingface_tensorflow_trcomp", "huggingface_pytorch_trcomp", "pytorch_trcomp", "tensorflow", "pytorch", "stabilityai_pytorch"]
-build_frameworks = []
+build_frameworks = ["vllm"]
 
 
 # By default we build both training and inference containers. Set true/false values to determine which to build.
-build_training = true
-build_inference = true
+build_training = false
+build_inference = false
 
 # Set do_build to "false" to skip builds and test the latest image built by this PR
 # Note: at least one build is required to set do_build to "false"
-do_build = true
+do_build = false
 
 [notify]
 ### Notify on test failures

eks_infrastructure/rbac.yaml

@@ -181,4 +181,80 @@ subjects:
 roleRef:
   kind: ClusterRole
   name: eks-cluster-role
+  apiGroup: rbac.authorization.k8s.io
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: Role
+metadata:
+  name: vllm-role
+  namespace: vllm
+rules:
+- apiGroups:
+  - ""
+  resources:
+  - pods
+  - pods/log
+  - services
+  - secrets
+  - persistentvolumeclaims 
+  verbs:
+  - get
+  - list
+  - create
+  - delete
+- apiGroups:
+  - "leaderworkerset.x-k8s.io"
+  resources:
+  - leaderworkersets
+  verbs:
+  - get
+  - create
+  - delete
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: vllm-cluster-role
+rules:
+- apiGroups:
+  - "networking.k8s.io"
+  resources:
+  - ingresses
+  verbs:
+  - get
+  - create
+  - delete
+- apiGroups:
+  - "storage.k8s.io"
+  resources:
+  - persistentvolumes
+  verbs:
+  - get
+  - create
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: RoleBinding
+metadata:
+  name: vllm-role-binding
+  namespace: vllm
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: vllm-role
+subjects:
+- apiGroup: rbac.authorization.k8s.io
+  kind: User
+  name: test-role
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: vllm-cluster-role-binding
+subjects:
+- kind: User
+  name: test-role
+  apiGroup: rbac.authorization.k8s.io
+roleRef:
+  kind: ClusterRole
+  name: vllm-cluster-role
   apiGroup: rbac.authorization.k8s.io

test/testrunner.py

@@ -311,7 +311,7 @@ def main():
     if (
         build_context == "MAINLINE"
         and all("base" in image_uri or "vllm" in image_uri for image_uri in all_image_list)
-        and test_type not in {"functionality_sanity", "security_sanity"}
+        and test_type not in {"functionality_sanity", "security_sanity", "eks", "ec2"}
     ):
         LOGGER.info(
             f"NOTE: {specific_test_type} tests not supported on base or vllm images. Skipping..."