From 64c02228d88e9e9767514352fcefaf3ebdf8004d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sebastian=20Kr=C3=BCger?= Date: Sun, 23 Nov 2025 16:17:27 +0100 Subject: [PATCH] fix: use EMPTY api_key for vLLM servers --- ai/litellm-config.yaml | 2 ++ 1 file changed, 2 insertions(+) diff --git a/ai/litellm-config.yaml b/ai/litellm-config.yaml index b73c189..849cbe5 100644 --- a/ai/litellm-config.yaml +++ b/ai/litellm-config.yaml @@ -34,6 +34,7 @@ model_list: litellm_params: model: hosted_vllm/openai/qwen-2.5-7b # hosted_vllm/openai/ prefix for proper streaming api_base: os.environ/GPU_VLLM_QWEN_URL # Direct to vLLM Qwen server + api_key: "EMPTY" # vLLM doesn't validate API keys rpm: 1000 tpm: 100000 timeout: 600 # 10 minutes for generation @@ -46,6 +47,7 @@ model_list: litellm_params: model: hosted_vllm/openai/llama-3.1-8b # hosted_vllm/openai/ prefix for proper streaming api_base: os.environ/GPU_VLLM_LLAMA_URL # Direct to vLLM Llama server + api_key: "EMPTY" # vLLM doesn't validate API keys rpm: 1000 tpm: 100000 timeout: 600 # 10 minutes for generation