From fe0cf487ee8193a88e2a80c869f9f2b5f19096da Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sebastian=20Kr=C3=BCger?= <valknar@pivoine.art>
Date: Fri, 21 Nov 2025 19:02:44 +0100
Subject: [PATCH] fix: use correct vLLM model name with hosted_vllm prefix

---
 ai/litellm-config.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/ai/litellm-config.yaml b/ai/litellm-config.yaml
index feb2560..6a029cc 100644
--- a/ai/litellm-config.yaml
+++ b/ai/litellm-config.yaml
@@ -32,7 +32,7 @@ model_list:
   # Text Generation
   - model_name: qwen-2.5-7b
     litellm_params:
-      model: openai/qwen-2.5-7b  # OpenAI-compatible vLLM endpoint
+      model: hosted_vllm/Qwen/Qwen2.5-7B-Instruct  # vLLM HuggingFace model name
       api_base: http://100.121.199.88:9000/v1  # RunPod GPU via Tailscale
       api_key: dummy
       rpm: 1000