feat/comfyui-gpu-rebalance
main
ornith.yaml
qwen-cpu.yaml
k8s/apps/comfyui/
58-comfyui.yaml
Gateway route update in separate PR (homelab-frontend).
GPU rebalance (4× V100 32GB on worker-1): - reasoning: 2 GPU (unchanged, PP=2 for Qwen3-32B) - ornith: 2→1 GPU (scale to 1 replica, ornith:35b only) - comfyui: 0→1 GPU (new) - embeddings/reranker: 0 GPU (CPU, unchanged) qwen2.5:3b-instruct moved to CPU on talos-cp-2 (144GB RAM). Separate Ollama deployment + 5Gi PVC, pulls model on first start. Gateway config updated in homelab-frontend (separate commit). Co-authored-by: poimen <[email protected]>
No dependencies set.
The note is not visible to the blocked user.
GPU Rebalance (4× V100 32GB)
Changes
ornith.yaml: scale 2→1, remove qwen2.5 co-loading, MAX_LOADED_MODELS=1qwen-cpu.yaml: new Ollama deployment on talos-cp-2 (144GB RAM), 5Gi PVCk8s/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).