From 57b706abe62c3b6b31890eb708a21436f57c7f16 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sebastian=20Kr=C3=BCger?= <valknar@pivoine.art>
Date: Fri, 21 Nov 2025 16:28:54 +0100
Subject: [PATCH] fix: correct vLLM service port to 8000

- Updated qwen-2.5-7b port from 8001 to 8000 in models.yaml
- Matches actual vLLM server default port configuration
- Tested and verified: orchestrator successfully loaded model and generated response
---
 model-orchestrator/models.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/model-orchestrator/models.yaml b/model-orchestrator/models.yaml
index d3e6a4b..613f0d2 100644
--- a/model-orchestrator/models.yaml
+++ b/model-orchestrator/models.yaml
@@ -7,7 +7,7 @@ models:
     type: text
     framework: vllm
     service_script: models/vllm/server.py
-    port: 8001
+    port: 8000
     vram_gb: 14
     startup_time_seconds: 120
     endpoint: /v1/chat/completions