Skip to content
CVE PROGRAM SOURCE RECORD6.5 Medium

CVE-2026-34756

vLLM Affected by Unauthenticated OOM Denial of Service via Unbounded `n` Parameter in OpenAI API Server

Read JSON ↗CVE.org ↗
Status
Published
Published
Updated
Assigning organization
GitHub_M

Description

vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.19.0, a Denial of Service vulnerability exists in the vLLM OpenAI-compatible API server. Due to the lack of an upper bound validation on the n parameter in the ChatCompletionRequest and CompletionRequest Pydantic models, an unauthenticated attacker can send a single HTTP request with an astronomically large n value. This completely blocks the Python asyncio event loop and causes immediate Out-Of-Memory crashes by allocating millions of request object copies in the heap before the request even reaches the scheduling queue. This vulnerability is fixed in 0.19.0.

Affected products

Version statuses are supplied by the assigning organization. Consult the original record for detailed ranges and platform conditions.

vllm-project vllm

  • >= 0.1.0, < 0.19.0affected

References