fix: add /v1 suffix to vLLM api_base for proper endpoint routing

2025-11-21 18:00:53 +01:00
parent 42a68bc0b5
commit dfde1df72f
1 changed files with 1 additions and 1 deletions
--- a/ai/litellm-config.yaml
+++ b/ai/litellm-config.yaml
@@ -33,7 +33,7 @@ model_list:
  - model_name: qwen-2.5-7b
    litellm_params:
      model: openai/qwen-2.5-7b
-      api_base: http://100.121.199.88:9000  # RunPod GPU via Tailscale (no /v1 suffix)
+      api_base: http://100.121.199.88:9000/v1  # RunPod GPU via Tailscale
      api_key: dummy
      rpm: 1000
      tpm: 100000