Skip to content

Add EKS test for vLLM #5008

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.

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

Closed
wants to merge 16 commits into from
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
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
8 changes: 4 additions & 4 deletions dlc_developer_config.toml
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down
76 changes: 76 additions & 0 deletions eks_infrastructure/rbac.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -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
2 changes: 1 addition & 1 deletion test/testrunner.py
Original file line number Diff line number Diff line change
Expand Up @@ -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..."
Expand Down
Empty file added test/vllm_tests/__init__.py
Empty file.
Empty file.
Loading
Loading