Live › vulnerability › CVE-2026-114051
Go to dashboardvLLM before 0.31.0 skips a token-limit validation check on /inference/v1/generate when max_tokens is null, so the engine's input thread crashes on an uncaught error. An unauthenticated remote attacker can send one request with an oversized min_tokens value to stop every later generation request until the service is restarted manually.
Summary written from the sources below. Check the originals before acting.
First seen by InfraStack 2026-10-23 21:57 UTC. All times on this page are UTC.
Any deployment running vLLM older than 0.31.0 with the /inference/v1/generate endpoint exposed to clients that can reach it. Deployments where that endpoint is only reachable from trusted internal callers, or that run a patched version, can skip this. The sources do not say whether the flaw depends on a non-default configuration.
No product ranges from the sources yet.
pip show vllm or python -c "import vllm; print(vllm.__version__)" on the serving host and compare against 0.31.00.31.0 or laterEach row is the first time that source carried this signal. The analyst’s rows are its own findings.
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.
This page as .md · .json · in your agent: get_signal("CVE-2026-114051")
NVD data is provided by NIST and is public domain · EPSS scores by FIRST, used with attribution. Posts quoted belong to their authors.