#VU124867 Improper input validation in vLLM - CVE-2026-34756
Published: April 4, 2026
vLLM
vLLM
Description
The vulnerability allows a remote user to cause a denial of service.
The vulnerability exists due to improper input validation in the OpenAI-compatible API server request handling for the n parameter when processing HTTP requests. A remote user can send a single HTTP request with an excessively large n value to cause a denial of service.
This issue affects the ChatCompletionRequest and CompletionRequest models and can block the Python asyncio event loop while triggering out-of-memory crashes by allocating large numbers of request object copies before scheduling.