rock
8790de6038
## GPU Rebalance (4× V100 32GB) | Pod | Before | After | |-----|--------|-------| | reasoning (PP=2) | 2 GPU | 2 GPU | | ornith | 2 GPU (2 replicas) | 1 GPU (1 replica) | | comfyui | — | 1 GPU (**new**) | | qwen-cpu | — | CPU on cp-2 (**new**) | | embeddings/reranker | CPU | CPU | ## Changes - `ornith.yaml`: scale 2→1, remove qwen2.5 co-loading, MAX_LOADED_MODELS=1 - `qwen-cpu.yaml`: new Ollama deployment on talos-cp-2 (144GB RAM), 5Gi PVC - `k8s/apps/comfyui/`: new ComfyUI deployment (1 GPU, 50Gi model PVC, ingress) - `58-comfyui.yaml`: ArgoCD Application (wave 8) Gateway route update in separate PR (homelab-frontend).Reviewed-on: #17 Co-authored-by: rock <[email protected]>
81 lines
1.9 KiB
YAML
81 lines
1.9 KiB
YAML
# ComfyUI — GPU-accelerated image generation on worker-1.
|
|
# Uses 1x V100 32GB (sm70). Freed by scaling ornith 2→1.
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: comfyui
|
|
namespace: comfyui
|
|
labels:
|
|
app: comfyui
|
|
spec:
|
|
replicas: 1
|
|
strategy:
|
|
type: Recreate
|
|
selector:
|
|
matchLabels:
|
|
app: comfyui
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app: comfyui
|
|
spec:
|
|
nodeSelector:
|
|
kubernetes.io/hostname: worker-1
|
|
runtimeClassName: nvidia
|
|
containers:
|
|
- name: comfyui
|
|
image: ghcr.io/ai-dock/comfyui:v2-cuda-12.1.1-base-22.04
|
|
ports:
|
|
- containerPort: 8188
|
|
protocol: TCP
|
|
env:
|
|
- name: NVIDIA_VISIBLE_DEVICES
|
|
value: "all"
|
|
- name: COMFYUI_FLAGS
|
|
value: "--listen 0.0.0.0 --port 8188"
|
|
resources:
|
|
requests:
|
|
cpu: "4"
|
|
memory: 8Gi
|
|
nvidia.com/gpu: "1"
|
|
limits:
|
|
cpu: "8"
|
|
memory: 16Gi
|
|
nvidia.com/gpu: "1"
|
|
volumeMounts:
|
|
- mountPath: /workspace/ComfyUI/models
|
|
name: models
|
|
- mountPath: /workspace/ComfyUI/output
|
|
name: output
|
|
readinessProbe:
|
|
httpGet:
|
|
path: /
|
|
port: 8188
|
|
periodSeconds: 10
|
|
initialDelaySeconds: 30
|
|
startupProbe:
|
|
httpGet:
|
|
path: /
|
|
port: 8188
|
|
failureThreshold: 60
|
|
periodSeconds: 10
|
|
volumes:
|
|
- name: models
|
|
persistentVolumeClaim:
|
|
claimName: comfyui-models
|
|
- name: output
|
|
emptyDir: {}
|
|
---
|
|
apiVersion: v1
|
|
kind: PersistentVolumeClaim
|
|
metadata:
|
|
name: comfyui-models
|
|
namespace: comfyui
|
|
spec:
|
|
accessModes:
|
|
- ReadWriteOnce
|
|
storageClassName: longhorn
|
|
resources:
|
|
requests:
|
|
storage: 50Gi
|