CVE-2026-114051 — Vulnerability intelligence
vllm — vllm
Published:
- CVSS
- 7.1
- CISA KEV
- Not listed; not proof of no exploitation
Original source text (not a translation)
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.