CVE-2026-114051

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.