From af7b654fb7e21894dd9cd6f0f27b37ce0bfd84bf Mon Sep 17 00:00:00 2001 From: Celes Renata Date: Sat, 4 Jul 2026 05:34:04 +0000 Subject: [PATCH] =?UTF-8?q?fix:=20vLLM=20deployment=20=E2=80=94=20Recreate?= =?UTF-8?q?=20strategy,=20correct=20service=20port,=20single=20model=20nam?= =?UTF-8?q?e?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - 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 --- infra/kube-vllm/deployment.yaml | 2 ++ infra/kube-vllm/service.yaml | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/infra/kube-vllm/deployment.yaml b/infra/kube-vllm/deployment.yaml index 9014954..c812d4d 100644 --- a/infra/kube-vllm/deployment.yaml +++ b/infra/kube-vllm/deployment.yaml @@ -7,6 +7,8 @@ metadata: app: vllm spec: replicas: 1 + strategy: + type: Recreate selector: matchLabels: app: vllm diff --git a/infra/kube-vllm/service.yaml b/infra/kube-vllm/service.yaml index 4bdc350..b97f202 100644 --- a/infra/kube-vllm/service.yaml +++ b/infra/kube-vllm/service.yaml @@ -23,7 +23,7 @@ spec: - nodePort: 31508 name: vllm-api port: 2701 - targetPort: 8000 + targetPort: 8080 selector: app: vllm-metrics type: LoadBalancer