feat: vLLM serving numind/NuExtract3 on full GPU, ollama disabled

- Ollama scaled to 0 — vLLM gets entire 16GB GPU
- NuExtract3 (9B) running at 80% GPU utilization
- Both OLLAMA_BASE_URL and VLLM_BASE_URL point to vLLM service
- Fixed gremlin-1 missing default route (no internet access)
- Removed GPU resource limit (time-slicing handles allocation)
- Removed init container (direct download works with internet fix)

infra/helm/stonks-oracle/values-beta.yaml

@@ -39,9 +39,9 @@ config:
   MINIO_SECURE: "false"
   BROKER_MODE: "paper"
   BROKER_PROVIDER: "alpaca"
-  OLLAMA_BASE_URL: "http://10.1.1.12:2701"
+  OLLAMA_BASE_URL: "http://nuextract-external.vllm-service.svc.cluster.local:2701"
-  OLLAMA_MODEL: "qwen3.5:4b-fast"
+  OLLAMA_MODEL: "numind/NuExtract3"
-  VLLM_BASE_URL: "http://vllm-external.vllm-service.svc.cluster.local:2701"
+  VLLM_BASE_URL: "http://nuextract-external.vllm-service.svc.cluster.local:2701"
   VLLM_MODEL: "numind/NuExtract3"
   VLLM_TIMEOUT: "120"
   VLLM_MAX_RETRIES: "2"

infra/helm/stonks-oracle/values-paper.yaml

@@ -16,9 +16,9 @@ config:
   REDIS_DB: "2"
   DEPLOY_STAGE: "paper"
   POSTGRES_USER: "stonks_paper"
-  OLLAMA_BASE_URL: "http://10.1.1.12:2701"
+  OLLAMA_BASE_URL: "http://nuextract-external.vllm-service.svc.cluster.local:2701"
-  OLLAMA_MODEL: "qwen3.5:4b-fast"
+  OLLAMA_MODEL: "numind/NuExtract3"
-  VLLM_BASE_URL: "http://vllm-external.vllm-service.svc.cluster.local:2701"
+  VLLM_BASE_URL: "http://nuextract-external.vllm-service.svc.cluster.local:2701"
   VLLM_MODEL: "numind/NuExtract3"
   MARKET_DATA_BASE_URL: "https://api.polygon.io"
 

infra/helm/stonks-oracle/values.yaml

@@ -185,14 +185,14 @@ config:
   REDIS_DB: "0"
   MINIO_ENDPOINT: "minio.minio-service.svc.cluster.local:80"
   MINIO_SECURE: "false"
-  OLLAMA_BASE_URL: "http://10.1.1.12:2701"
+  OLLAMA_BASE_URL: "http://nuextract-external.vllm-service.svc.cluster.local:2701"
-  OLLAMA_MODEL: "qwen3.5:4b-fast"
+  OLLAMA_MODEL: "numind/NuExtract3"
   OLLAMA_TIMEOUT: "240"
   OLLAMA_MAX_RETRIES: "2"
   OLLAMA_RETRY_BASE_DELAY: "1.0"
   OLLAMA_RETRY_MAX_DELAY: "10.0"
   OLLAMA_RETRY_BACKOFF_MULTIPLIER: "2.0"
-  VLLM_BASE_URL: "http://vllm-external.vllm-service.svc.cluster.local:2701"
+  VLLM_BASE_URL: "http://nuextract-external.vllm-service.svc.cluster.local:2701"
   VLLM_MODEL: "numind/NuExtract3"
   VLLM_TIMEOUT: "120"
   VLLM_MAX_RETRIES: "2"

infra/kube-vllm/deployment.yaml

@@ -16,6 +16,7 @@ spec:
         app: vllm
     spec:
       runtimeClassName: nvidia
+      enableServiceLinks: false
       nodeSelector:
         kubernetes.io/hostname: gremlin-1
       containers:
@@ -32,7 +33,7 @@ spec:
             - "--port"
             - "8000"
             - "--gpu-memory-utilization"
-            - "0.45"
+            - "0.80"
             - "--max-model-len"
             - "8192"
             - "--max-num-seqs"

infra/kube-vllm/service.yaml

@@ -1,7 +1,7 @@
 apiVersion: v1
 kind: Service
 metadata:
-  name: vllm
+  name: nuextract
   namespace: vllm-service
 spec:
   ports:
@@ -16,7 +16,7 @@ spec:
 apiVersion: v1
 kind: Service
 metadata:
-  name: vllm-external
+  name: nuextract-external
   namespace: vllm-service
 spec:
   ports:

infra/kube-vllm/vllm-metrics.yaml

@@ -37,7 +37,7 @@ metadata:
 data:
   default.conf: |
     upstream vllm_backend {
-        server vllm.vllm-service.svc.cluster.local:8000;
+        server nuextract.vllm-service.svc.cluster.local:8000;
     }
 
     server {