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:
@@ -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"
|
||||
|
||||
@@ -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"
|
||||
|
||||
|
||||
@@ -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"
|
||||
|
||||
Reference in New Issue
Block a user