A flaw was found in the server implementation of vLLM, where the handling of Jinja templates does not properly validate user-supplied input through the chat_template and chat_template_kwargs parameters. When a specially crafted template is processed, it can trigger excessive looping or recursion inside the Jinja engine, consuming large amounts of CPU and memory. This can cause the server to become unresponsive or crash, resulting in a denial-of-service (DoS) condition for applications using vLLM.

vLLM: Resource-Exhaustion (DoS) through Malicious Jinja Template in OpenAI-Compatible Server