CVE-2026-114051

No fix known EPSS <1%CVSS 7.5

vLLM before 0.31.0 skips the min_tokens <= max_tokens check for /inference/v1/generate requests with a null max_tokens, so the EngineCore input thread later dies on an uncaught VLLMValidationError while /health still returns 200. Unauthenticated remote attackers can send one request with an oversized min_tokens to hang all subsequent generation requests until manual restart.

Published 2026-10-21 · CVE record · OSV

Products: vllm-project vllm