Celes Renata af7b654fb7 fix: vLLM deployment — Recreate strategy, correct service port, single model name ...

- Strategy: Recreate (GPU can only be used by one pod at a time)
- nuextract-external targetPort: 8080 (nginx proxy port)
- served-model-name: numind/NuExtract3
- DB ai_agents updated to model=numind/NuExtract3 provider=vllm

2026-07-04 05:34:04 +00:00

..

deployment.yaml

fix: vLLM deployment — Recreate strategy, correct service port, single model name

2026-07-04 05:34:04 +00:00

monitor.sh

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

2026-07-03 17:02:31 +00:00

service.yaml

fix: vLLM deployment — Recreate strategy, correct service port, single model name

2026-07-04 05:34:04 +00:00

storage.yaml

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

2026-07-03 17:02:31 +00:00

values.yaml

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

2026-07-03 17:02:31 +00:00

vllm-metrics.yaml

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

2026-07-03 17:57:19 +00:00