feat: vLLM in K8s via Harbor mirror, pipelines point to internal svc

- vLLM image mirrored to registry.celestium.life/stonks-oracle/vllm-openai
- Deployment uses Harbor image (Docker Hub IPv6 unreachable from cluster)
- All 3 pipelines use vllm-external.vllm-service.svc.cluster.local:2701
- K8s manifests at infra/kube-vllm/ and synced to ~/sources/kube/vllm
This commit is contained in:
Celes Renata
2026-07-03 17:02:31 +00:00
parent 3a9894cd03
commit ecade0dd52
9 changed files with 354 additions and 3 deletions
+1 -1
View File
@@ -41,7 +41,7 @@ config:
BROKER_PROVIDER: "alpaca"
OLLAMA_BASE_URL: "http://10.1.1.12:2701"
OLLAMA_MODEL: "qwen3.5:4b-fast"
VLLM_BASE_URL: "http://192.168.42.254:2701"
VLLM_BASE_URL: "http://vllm-external.vllm-service.svc.cluster.local:2701"
VLLM_MODEL: "numind/NuExtract3"
VLLM_TIMEOUT: "120"
VLLM_MAX_RETRIES: "2"
+1 -1
View File
@@ -18,7 +18,7 @@ config:
POSTGRES_USER: "stonks_paper"
OLLAMA_BASE_URL: "http://10.1.1.12:2701"
OLLAMA_MODEL: "qwen3.5:4b-fast"
VLLM_BASE_URL: "http://192.168.42.254:2701"
VLLM_BASE_URL: "http://vllm-external.vllm-service.svc.cluster.local:2701"
VLLM_MODEL: "numind/NuExtract3"
MARKET_DATA_BASE_URL: "https://api.polygon.io"
+1 -1
View File
@@ -192,7 +192,7 @@ config:
OLLAMA_RETRY_BASE_DELAY: "1.0"
OLLAMA_RETRY_MAX_DELAY: "10.0"
OLLAMA_RETRY_BACKOFF_MULTIPLIER: "2.0"
VLLM_BASE_URL: "http://192.168.42.254:2701"
VLLM_BASE_URL: "http://vllm-external.vllm-service.svc.cluster.local:2701"
VLLM_MODEL: "numind/NuExtract3"
VLLM_TIMEOUT: "120"
VLLM_MAX_RETRIES: "2"