198 lines
5.1 KiB
YAML
198 lines
5.1 KiB
YAML
# -- Default values for chart vllm-omni
|
|
# -- Declare variables to be passed into your templates.
|
|
|
|
# -- HuggingFace model ID to serve
|
|
model: "Tongyi-MAI/Z-Image-Turbo"
|
|
|
|
# -- Image configuration
|
|
image:
|
|
# -- Image repository
|
|
repository: "vllm/vllm-omni"
|
|
# -- Image tag
|
|
tag: "v0.16.0"
|
|
# -- Override the container command entirely. If empty, the chart constructs
|
|
# -- it automatically from model + omniArgs.
|
|
command: []
|
|
# -- Optional environment variables for the container
|
|
env: []
|
|
# -- Security context override
|
|
securityContext: {}
|
|
|
|
# -- Container port
|
|
containerPort: 8000
|
|
# -- Service name (auto-generated from release name if empty)
|
|
serviceName:
|
|
# -- Service port
|
|
servicePort: 80
|
|
# -- Additional ports configuration
|
|
extraPorts: []
|
|
|
|
# -- Number of replicas
|
|
replicaCount: 1
|
|
|
|
# -- Deployment strategy configuration
|
|
deploymentStrategy: {}
|
|
|
|
# -- Resource configuration
|
|
resources:
|
|
requests:
|
|
# -- Number of CPUs
|
|
cpu: 4
|
|
# -- CPU memory
|
|
memory: 24Gi
|
|
# -- Number of GPUs
|
|
nvidia.com/gpu: 1
|
|
limits:
|
|
# -- Number of CPUs
|
|
cpu: 4
|
|
# -- CPU memory
|
|
memory: 24Gi
|
|
# -- Number of GPUs
|
|
nvidia.com/gpu: 1
|
|
|
|
# -- GPU model types for node affinity scheduling (optional)
|
|
# -- Leave empty to schedule on any GPU node. Set to restrict to specific GPU types.
|
|
# -- Example: ["NVIDIA-A100-SXM4-40GB"]
|
|
gpuModels: []
|
|
|
|
# -- vllm-omni specific CLI arguments
|
|
omniArgs:
|
|
# -- Additional raw CLI flags appended to the serve command (list of strings)
|
|
extraArgs: []
|
|
# -- Enable VAE slicing for memory optimization
|
|
vaeUseSlicing: false
|
|
# -- Enable VAE tiling for memory optimization
|
|
vaeUseTiling: false
|
|
# -- Enable CPU offloading for diffusion models
|
|
enableCpuOffload: false
|
|
# -- Number of GPUs for diffusion inference (empty = auto)
|
|
numGpus:
|
|
# -- Path to stage configs file (empty = auto-detected from model)
|
|
stageConfigsPath:
|
|
# -- Cache backend: none, tea_cache, or cache_dit
|
|
cacheBackend: "none"
|
|
# -- Default sampling params as a JSON string
|
|
defaultSamplingParams:
|
|
# -- Worker backend: multi_process or ray
|
|
workerBackend: "multi_process"
|
|
|
|
# -- HuggingFace token for gated models (optional)
|
|
hfToken: ""
|
|
|
|
# -- Shared memory size for PyTorch multiprocessing
|
|
shmSize: "8Gi"
|
|
|
|
# -- Model cache configuration (HuggingFace downloads)
|
|
modelCache:
|
|
# -- Use a PersistentVolumeClaim for model cache (recommended for production)
|
|
enabled: true
|
|
# -- Storage size for the PVC
|
|
storageSize: "50Gi"
|
|
# -- Storage class name (empty = cluster default)
|
|
storageClassName: ""
|
|
# -- Access modes
|
|
accessModes:
|
|
- ReadWriteOnce
|
|
|
|
# -- Autoscaling configuration
|
|
autoscaling:
|
|
# -- Enable autoscaling
|
|
enabled: false
|
|
# -- Minimum replicas
|
|
minReplicas: 1
|
|
# -- Maximum replicas
|
|
maxReplicas: 10
|
|
# -- Target CPU utilization for autoscaling
|
|
targetCPUUtilizationPercentage: 80
|
|
# targetMemoryUtilizationPercentage: 80
|
|
|
|
# -- ConfigMap data (key-value pairs injected as environment variables)
|
|
configs: {}
|
|
|
|
# -- Secrets data (key-value pairs, base64-encoded automatically)
|
|
secrets: {}
|
|
|
|
# -- External ConfigMaps/Secrets references
|
|
externalConfigs: []
|
|
|
|
# -- Custom Kubernetes objects
|
|
customObjects: []
|
|
|
|
# -- PodDisruptionBudget max unavailable
|
|
maxUnavailablePodDisruptionBudget: ""
|
|
|
|
# -- Additional init containers
|
|
extraInit:
|
|
initContainers: []
|
|
|
|
# -- Additional sidecar containers
|
|
extraContainers: []
|
|
|
|
# -- Startup probe configuration
|
|
# -- Protects slow-starting containers. Liveness and readiness probes
|
|
# -- do not start until the startup probe succeeds.
|
|
# -- failureThreshold * periodSeconds = max startup time (40 * 30 = 1200s = 20 min)
|
|
startupProbe:
|
|
# -- HTTP check configuration
|
|
httpGet:
|
|
# -- Path to check
|
|
path: /health
|
|
# -- Port to check (uses named port to stay in sync with containerPort)
|
|
port: "container-port"
|
|
# -- Failures before killing the container
|
|
failureThreshold: 40
|
|
# -- How often to perform the probe
|
|
periodSeconds: 30
|
|
|
|
# -- Readiness probe configuration
|
|
readinessProbe:
|
|
# -- How often to perform the probe
|
|
periodSeconds: 10
|
|
# -- Failures before marking unready
|
|
failureThreshold: 3
|
|
# -- HTTP check configuration
|
|
httpGet:
|
|
# -- Path to check
|
|
path: /health
|
|
# -- Port to check (uses named port to stay in sync with containerPort)
|
|
port: "container-port"
|
|
|
|
# -- Liveness probe configuration
|
|
livenessProbe:
|
|
# -- Failures before restarting
|
|
failureThreshold: 3
|
|
# -- How often to perform the probe
|
|
periodSeconds: 15
|
|
# -- HTTP check configuration
|
|
httpGet:
|
|
# -- Path to check
|
|
path: /health
|
|
# -- Port to check (uses named port to stay in sync with containerPort)
|
|
port: "container-port"
|
|
|
|
# -- Ingress configuration
|
|
ingress:
|
|
# -- Enable Ingress
|
|
enabled: false
|
|
# -- Ingress class name (e.g., nginx, traefik)
|
|
ingressClassName: ""
|
|
# -- Hostname for the Ingress rule
|
|
host: "vllm-omni.example.com"
|
|
# -- Additional annotations
|
|
annotations: {}
|
|
# -- TLS configuration
|
|
tls: []
|
|
# - secretName: vllm-omni-tls
|
|
# hosts:
|
|
# - vllm-omni.example.com
|
|
|
|
# -- Node selector for pod scheduling
|
|
nodeSelector: {}
|
|
|
|
# -- Tolerations for pod scheduling
|
|
tolerations: []
|
|
|
|
# -- Labels applied to all resources
|
|
labels:
|
|
app: "vllm-omni"
|