[Feature] Add Helm Chart to deploy vLLM-Omni on Kubernetes (#1337)
Signed-off-by: Ricardo Noriega De Soto <rnoriega@redhat.com>
This commit is contained in:
Ricardo Noriega authored and GitHub committed
1 parent
e79ad8d59a
commit
112a9aa237
21 files changed
+1250
No files matched your search
@@ -0,0 +1,181 @@
|
||||
suite: test deployment
|
||||
templates:
|
||||
- deployment.yaml
|
||||
tests:
|
||||
- it: should create deployment with default omni command
|
||||
asserts:
|
||||
- hasDocuments:
|
||||
count: 1
|
||||
- isKind:
|
||||
of: Deployment
|
||||
- equal:
|
||||
path: spec.template.spec.containers[0].name
|
||||
value: vllm-omni
|
||||
- equal:
|
||||
path: spec.template.spec.containers[0].command[0]
|
||||
value: vllm
|
||||
- equal:
|
||||
path: spec.template.spec.containers[0].command[1]
|
||||
value: serve
|
||||
- equal:
|
||||
path: spec.template.spec.containers[0].command[2]
|
||||
value: Tongyi-MAI/Z-Image-Turbo
|
||||
- equal:
|
||||
path: spec.template.spec.containers[0].command[3]
|
||||
value: "--omni"
|
||||
- equal:
|
||||
path: spec.template.spec.containers[0].command[4]
|
||||
value: "--host"
|
||||
- equal:
|
||||
path: spec.template.spec.containers[0].command[5]
|
||||
value: "0.0.0.0"
|
||||
- equal:
|
||||
path: spec.template.spec.containers[0].command[6]
|
||||
value: "--port"
|
||||
- equal:
|
||||
path: spec.template.spec.containers[0].command[7]
|
||||
value: "8000"
|
||||
|
||||
- it: should use custom model when set
|
||||
set:
|
||||
model: "Qwen/Qwen2.5-Omni-7B"
|
||||
asserts:
|
||||
- equal:
|
||||
path: spec.template.spec.containers[0].command[2]
|
||||
value: Qwen/Qwen2.5-Omni-7B
|
||||
|
||||
- it: should include omniArgs flags in command
|
||||
set:
|
||||
omniArgs:
|
||||
vaeUseSlicing: true
|
||||
vaeUseTiling: true
|
||||
enableCpuOffload: true
|
||||
numGpus: 2
|
||||
cacheBackend: "tea_cache"
|
||||
workerBackend: "ray"
|
||||
extraArgs:
|
||||
- "--enable-layerwise-offload"
|
||||
asserts:
|
||||
- contains:
|
||||
path: spec.template.spec.containers[0].command
|
||||
content: "--vae-use-slicing"
|
||||
- contains:
|
||||
path: spec.template.spec.containers[0].command
|
||||
content: "--vae-use-tiling"
|
||||
- contains:
|
||||
path: spec.template.spec.containers[0].command
|
||||
content: "--enable-cpu-offload"
|
||||
- contains:
|
||||
path: spec.template.spec.containers[0].command
|
||||
content: "--num-gpus"
|
||||
- contains:
|
||||
path: spec.template.spec.containers[0].command
|
||||
content: "--cache-backend"
|
||||
- contains:
|
||||
path: spec.template.spec.containers[0].command
|
||||
content: "--worker-backend"
|
||||
- contains:
|
||||
path: spec.template.spec.containers[0].command
|
||||
content: "--enable-layerwise-offload"
|
||||
|
||||
- it: should use full command override when image.command is set
|
||||
set:
|
||||
image:
|
||||
command:
|
||||
- "custom-binary"
|
||||
- "--flag"
|
||||
asserts:
|
||||
- equal:
|
||||
path: spec.template.spec.containers[0].command[0]
|
||||
value: custom-binary
|
||||
- equal:
|
||||
path: spec.template.spec.containers[0].command[1]
|
||||
value: "--flag"
|
||||
|
||||
- it: should mount shm and model-cache volumes
|
||||
asserts:
|
||||
- contains:
|
||||
path: spec.template.spec.containers[0].volumeMounts
|
||||
content:
|
||||
name: shm
|
||||
mountPath: /dev/shm
|
||||
- contains:
|
||||
path: spec.template.spec.containers[0].volumeMounts
|
||||
content:
|
||||
name: model-cache
|
||||
mountPath: /cache
|
||||
- contains:
|
||||
path: spec.template.spec.volumes
|
||||
content:
|
||||
name: shm
|
||||
emptyDir:
|
||||
medium: Memory
|
||||
sizeLimit: 8Gi
|
||||
|
||||
- it: should use PVC for model-cache when modelCache is enabled
|
||||
set:
|
||||
modelCache:
|
||||
enabled: true
|
||||
storageSize: "50Gi"
|
||||
accessModes:
|
||||
- ReadWriteOnce
|
||||
asserts:
|
||||
- contains:
|
||||
path: spec.template.spec.volumes
|
||||
content:
|
||||
name: model-cache
|
||||
persistentVolumeClaim:
|
||||
claimName: RELEASE-NAME-model-cache
|
||||
|
||||
- it: should use emptyDir for model-cache when modelCache is disabled
|
||||
set:
|
||||
modelCache:
|
||||
enabled: false
|
||||
storageSize: "50Gi"
|
||||
accessModes:
|
||||
- ReadWriteOnce
|
||||
asserts:
|
||||
- contains:
|
||||
path: spec.template.spec.volumes
|
||||
content:
|
||||
name: model-cache
|
||||
emptyDir: {}
|
||||
|
||||
- it: should set HF_HOME environment variable
|
||||
asserts:
|
||||
- contains:
|
||||
path: spec.template.spec.containers[0].env
|
||||
content:
|
||||
name: HF_HOME
|
||||
value: /cache/huggingface
|
||||
|
||||
- it: should set HF_TOKEN env when hfToken is provided
|
||||
set:
|
||||
hfToken: "hf_test_token_123"
|
||||
asserts:
|
||||
- contains:
|
||||
path: spec.template.spec.containers[0].env
|
||||
content:
|
||||
name: HF_TOKEN
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: RELEASE-NAME-hf-token
|
||||
key: token
|
||||
|
||||
- it: should create custom init containers when specified
|
||||
set:
|
||||
extraInit:
|
||||
initContainers:
|
||||
- name: my-init
|
||||
image: busybox:latest
|
||||
command: ["echo", "init"]
|
||||
asserts:
|
||||
- lengthEqual:
|
||||
path: spec.template.spec.initContainers
|
||||
count: 1
|
||||
- equal:
|
||||
path: spec.template.spec.initContainers[0].name
|
||||
value: my-init
|
||||
- equal:
|
||||
path: spec.template.spec.initContainers[0].image
|
||||
value: busybox:latest
|
||||
@@ -0,0 +1,86 @@
|
||||
suite: test ingress
|
||||
templates:
|
||||
- ingress.yaml
|
||||
tests:
|
||||
- it: should not create Ingress when disabled
|
||||
set:
|
||||
ingress:
|
||||
enabled: false
|
||||
asserts:
|
||||
- hasDocuments:
|
||||
count: 0
|
||||
|
||||
- it: should create Ingress when enabled
|
||||
set:
|
||||
ingress:
|
||||
enabled: true
|
||||
host: "vllm-omni.example.com"
|
||||
asserts:
|
||||
- hasDocuments:
|
||||
count: 1
|
||||
- isKind:
|
||||
of: Ingress
|
||||
- equal:
|
||||
path: spec.rules[0].host
|
||||
value: vllm-omni.example.com
|
||||
- equal:
|
||||
path: spec.rules[0].http.paths[0].path
|
||||
value: /
|
||||
- equal:
|
||||
path: spec.rules[0].http.paths[0].pathType
|
||||
value: Prefix
|
||||
- equal:
|
||||
path: spec.rules[0].http.paths[0].backend.service.name
|
||||
value: RELEASE-NAME-service
|
||||
- equal:
|
||||
path: spec.rules[0].http.paths[0].backend.service.port.number
|
||||
value: 80
|
||||
|
||||
- it: should set ingressClassName when specified
|
||||
set:
|
||||
ingress:
|
||||
enabled: true
|
||||
host: "vllm-omni.example.com"
|
||||
ingressClassName: "nginx"
|
||||
asserts:
|
||||
- equal:
|
||||
path: spec.ingressClassName
|
||||
value: nginx
|
||||
|
||||
- it: should not set ingressClassName when empty
|
||||
set:
|
||||
ingress:
|
||||
enabled: true
|
||||
host: "vllm-omni.example.com"
|
||||
ingressClassName: ""
|
||||
asserts:
|
||||
- notExists:
|
||||
path: spec.ingressClassName
|
||||
|
||||
- it: should include annotations when specified
|
||||
set:
|
||||
ingress:
|
||||
enabled: true
|
||||
host: "vllm-omni.example.com"
|
||||
annotations:
|
||||
nginx.ingress.kubernetes.io/proxy-body-size: "100m"
|
||||
asserts:
|
||||
- isNotEmpty:
|
||||
path: metadata.annotations
|
||||
|
||||
- it: should include TLS configuration when specified
|
||||
set:
|
||||
ingress:
|
||||
enabled: true
|
||||
host: "vllm-omni.example.com"
|
||||
tls:
|
||||
- secretName: vllm-omni-tls
|
||||
hosts:
|
||||
- vllm-omni.example.com
|
||||
asserts:
|
||||
- equal:
|
||||
path: spec.tls[0].secretName
|
||||
value: vllm-omni-tls
|
||||
- equal:
|
||||
path: spec.tls[0].hosts[0]
|
||||
value: vllm-omni.example.com
|
||||
@@ -0,0 +1,73 @@
|
||||
suite: test pvc
|
||||
templates:
|
||||
- pvc.yaml
|
||||
tests:
|
||||
- it: should create PVC when modelCache is enabled
|
||||
set:
|
||||
modelCache:
|
||||
enabled: true
|
||||
storageSize: "50Gi"
|
||||
storageClassName: ""
|
||||
accessModes:
|
||||
- ReadWriteOnce
|
||||
asserts:
|
||||
- hasDocuments:
|
||||
count: 1
|
||||
- isKind:
|
||||
of: PersistentVolumeClaim
|
||||
- equal:
|
||||
path: spec.accessModes[0]
|
||||
value: ReadWriteOnce
|
||||
- equal:
|
||||
path: spec.resources.requests.storage
|
||||
value: 50Gi
|
||||
|
||||
- it: should not create PVC when modelCache is disabled
|
||||
set:
|
||||
modelCache:
|
||||
enabled: false
|
||||
storageSize: "50Gi"
|
||||
accessModes:
|
||||
- ReadWriteOnce
|
||||
asserts:
|
||||
- hasDocuments:
|
||||
count: 0
|
||||
|
||||
- it: should use custom storage size
|
||||
set:
|
||||
modelCache:
|
||||
enabled: true
|
||||
storageSize: "100Gi"
|
||||
storageClassName: ""
|
||||
accessModes:
|
||||
- ReadWriteOnce
|
||||
asserts:
|
||||
- equal:
|
||||
path: spec.resources.requests.storage
|
||||
value: 100Gi
|
||||
|
||||
- it: should set storageClassName when specified
|
||||
set:
|
||||
modelCache:
|
||||
enabled: true
|
||||
storageSize: "50Gi"
|
||||
storageClassName: "fast-ssd"
|
||||
accessModes:
|
||||
- ReadWriteOnce
|
||||
asserts:
|
||||
- equal:
|
||||
path: spec.storageClassName
|
||||
value: fast-ssd
|
||||
|
||||
- it: should support ReadWriteMany access mode
|
||||
set:
|
||||
modelCache:
|
||||
enabled: true
|
||||
storageSize: "50Gi"
|
||||
storageClassName: ""
|
||||
accessModes:
|
||||
- ReadWriteMany
|
||||
asserts:
|
||||
- equal:
|
||||
path: spec.accessModes[0]
|
||||
value: ReadWriteMany
|
||||
@@ -0,0 +1,48 @@
|
||||
suite: test secrets
|
||||
templates:
|
||||
- secrets.yaml
|
||||
tests:
|
||||
- it: should create HF token secret when hfToken is provided
|
||||
set:
|
||||
hfToken: "hf_test_token_123"
|
||||
asserts:
|
||||
- hasDocuments:
|
||||
count: 1
|
||||
- isKind:
|
||||
of: Secret
|
||||
- equal:
|
||||
path: metadata.name
|
||||
value: RELEASE-NAME-hf-token
|
||||
- exists:
|
||||
path: data.token
|
||||
|
||||
- it: should not create any secrets when hfToken is empty and no secrets defined
|
||||
set:
|
||||
hfToken: ""
|
||||
secrets: {}
|
||||
asserts:
|
||||
- hasDocuments:
|
||||
count: 0
|
||||
|
||||
- it: should create both generic and HF token secrets
|
||||
set:
|
||||
hfToken: "hf_test_token_123"
|
||||
secrets:
|
||||
mykey: myvalue
|
||||
asserts:
|
||||
- hasDocuments:
|
||||
count: 2
|
||||
|
||||
- it: should create only generic secrets when no hfToken
|
||||
set:
|
||||
hfToken: ""
|
||||
secrets:
|
||||
mykey: myvalue
|
||||
asserts:
|
||||
- hasDocuments:
|
||||
count: 1
|
||||
- isKind:
|
||||
of: Secret
|
||||
- equal:
|
||||
path: metadata.name
|
||||
value: RELEASE-NAME-secrets
|
||||
Reference in new issue
Block a user