feat: add ComfyUI, rebalance GPU allocation

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]>

This commit is contained in:

rock

2026-09-08 18:26:07 -07:00

co-authored by

poimen

parent c5aadd98f8

commit 39f5fe3683

8 changed files with 281 additions and 16 deletions

									
										k8s/apps/comfyui/kustomization.yaml
									
		+7
		
												View File
												
				@@ -0,0 +1,7 @@

				apiVersion: kustomize.config.k8s.io/v1beta1

				kind: Kustomization

				resources:

				  - deployment.yaml

				  - service.yaml

				  - ingress.yaml