fix: use hosted_vllm/openai/ prefix for vLLM model via orchestrator

2025-11-21 19:18:33 +01:00
parent 155016da97
commit ec903c16c2
1 changed files with 1 additions and 1 deletions
--- 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: hosted_vllm/qwen-2.5-7b  # vLLM model ID from /v1/models endpoint
+      model: hosted_vllm/openai/qwen-2.5-7b  # hosted_vllm/openai/ for vLLM via orchestrator
      api_base: http://100.121.199.88:9000/v1  # RunPod GPU via Tailscale
      api_key: dummy
      rpm: 1000