diff --git a/llama_stack/templates/remote-vllm/run.yaml b/llama_stack/templates/remote-vllm/run.yaml index b6bba1252..1f3cdfb39 100644 --- a/llama_stack/templates/remote-vllm/run.yaml +++ b/llama_stack/templates/remote-vllm/run.yaml @@ -15,7 +15,7 @@ providers: - provider_id: vllm-inference provider_type: remote::vllm config: - url: ${env.VLLM_URL} + url: ${env.VLLM_URL:http://localhost:8000/v1} max_tokens: ${env.VLLM_MAX_TOKENS:4096} api_token: ${env.VLLM_API_TOKEN:fake} tls_verify: ${env.VLLM_TLS_VERIFY:true}