From bf273f24a8187a26b7c47b6b715927831b6cfe34 Mon Sep 17 00:00:00 2001 From: Amgad Elgamal Date: Thu, 2 Oct 2025 21:12:39 -0400 Subject: [PATCH] Corrected command syntax for serving the model with vLLM. --- docs/quickstart.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/quickstart.md b/docs/quickstart.md index 8f4cb7ba..311eed2d 100644 --- a/docs/quickstart.md +++ b/docs/quickstart.md @@ -17,7 +17,7 @@ We'll need to serve our model on an inference server with vLLM. The following wi uv tool install vllm # Serve the model locally -uvx --with setuptools serve allenai/OLMo-1B-hf --dtype auto --api-key MY_KEY --chat-template chat_templates/omlo-chat-template.jinja +uvx --with setuptools vllm serve allenai/OLMo-1B-hf --dtype auto --api-key MY_KEY --chat-template chat_templates/olmo-chat-template.jinja ``` Some things to keep in mind: