fix: revert to openai prefix, remove /v1 suffix from api_base

- Changed back from hosted_vllm/qwen-2.5-7b to openai/qwen-2.5-7b
- Removed /v1 suffix from api_base (LiteLLM adds it automatically)
- Added supports_system_messages: false for vLLM compatibility

ai/litellm-config.yaml

@@ -32,13 +32,14 @@ model_list:
   # Text Generation
   - model_name: qwen-2.5-7b
     litellm_params:
-      model: hosted_vllm/qwen-2.5-7b
-      api_base: http://100.121.199.88:9000/v1  # RunPod GPU via Tailscale
+      model: openai/qwen-2.5-7b
+      api_base: http://100.121.199.88:9000  # RunPod GPU via Tailscale (no /v1 suffix)
       api_key: dummy
       rpm: 1000
       tpm: 100000
       timeout: 600  # 10 minutes for generation
       stream_timeout: 600
+      supports_system_messages: false  # vLLM handles system messages differently
 
   # Image Generation
   - model_name: flux-schnell