NetSight
IP …
medium6.5

CVE-2026-34756

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

Impact

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 packages

EcosystemPackageAffectedFixed in
pipvllm>= 0.1.0, < 0.19.00.19.0

Affected products

VendorProductAffected versions
VllmVllm
from 0.1.0 before 0.19.0

Weakness classification

CWE-770CWE-1284

References