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]>

k8s/apps/llm-serving/ornith.yaml

@@ -33,12 +33,8 @@ spec:
 
         ollama pull ornith:35b
 
-        ollama pull qwen2.5:3b-instruct
-
         ollama run ornith:35b "ok" >/dev/null 2>&1 || true
 
-        ollama run qwen2.5:3b-instruct "ok" >/dev/null 2>&1 || true
-
         wait $SERVE_PID
 
         '
@@ -54,7 +50,7 @@ spec:
       - name: OLLAMA_NUM_PARALLEL
         value: '1'
       - name: OLLAMA_MAX_LOADED_MODELS
-        value: '2'
+        value: '1'
       image: ollama/ollama:0.32.9@sha256:1685741456770df6e3cceb2a945a5f75e020f658d1701509668d6f4688f1dd3f
       name: kserve-container
       ports:
@@ -65,8 +61,7 @@ spec:
           command:
           - /bin/sh
           - -c
-          - ollama ps 2>/dev/null | grep -q ornith && ollama ps 2>/dev/null |
-            grep -q qwen2.5
+          - ollama ps 2>/dev/null | grep -q ornith
         periodSeconds: 10
       resources:
         limits:
@@ -82,8 +77,7 @@ spec:
           command:
           - /bin/sh
           - -c
-          - ollama ps 2>/dev/null | grep -q ornith && ollama ps 2>/dev/null |
-            grep -q qwen2.5
+          - ollama ps 2>/dev/null | grep -q ornith
         failureThreshold: 120
         periodSeconds: 15
       volumeMounts:
@@ -91,13 +85,10 @@ spec:
         name: models
     deploymentStrategy:
       type: Recreate
-    # 2 replicas -- each its own GPU, each loading both ornith:35b and
-    # qwen2.5:3b-instruct -- so 2 concurrent implementer-style calls each
-    # get an independent instance instead of contending on one, at the
-    # cost of judge/qwen traffic still sharing whichever replica an
-    # implementer call also lands on.
-    maxReplicas: 2
-    minReplicas: 2
+    # 1 replica -- ornith:35b only. qwen2.5:3b moved to CPU on cp-2.
+    # Frees 1 GPU for ComfyUI.
+    maxReplicas: 1
+    minReplicas: 1
     nodeSelector:
       kubernetes.io/hostname: worker-1
     runtimeClassName: nvidia