From 94080da3417fd929816f20432f6335e02b66f2eb Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sebastian=20Kr=C3=BCger?= <valknar@pivoine.art>
Date: Fri, 21 Nov 2025 18:10:53 +0100
Subject: [PATCH] fix: remove incorrect start-vllm.sh that would break
 orchestrator architecture

---
 start-vllm.sh | 12 ------------
 1 file changed, 12 deletions(-)
 delete mode 100755 start-vllm.sh

diff --git a/start-vllm.sh b/start-vllm.sh
deleted file mode 100755
index ee613a9..0000000
--- a/start-vllm.sh
+++ /dev/null
@@ -1,12 +0,0 @@
-#!/bin/bash
-# Start vLLM server with OpenAI-compatible API
-# This uses vLLM's built-in server which properly handles streaming
-
-vllm serve Qwen/Qwen2.5-7B-Instruct \
-  --host 0.0.0.0 \
-  --port 9000 \
-  --tensor-parallel-size 1 \
-  --gpu-memory-utilization 0.85 \
-  --max-model-len 4096 \
-  --download-dir /workspace/huggingface_cache \
-  --trust-remote-code