CVE-2026-114051GHSA-4xqp-c3mv-qff7
vLLM before 0.31.0 Denial of Service via min_tokens in /inference/v1/generate
vllm-project vllm
CVSS
7.1HighExploitationNo known exploitationNot in CISA KEV, which does not prove it is unexploitedCISA KEV
Exploit odds (EPSS)0.38%Chance of exploitation activity in the next 30 days, higher than 30% of CVEs. Scored 23 Oct 2026FIRST EPSS
What fixes it
- 0.31.0vllmCVE List
A fixed version on one release line is not the upgrade target for every line. Check your exact version and any vendor backports.
Description
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.
Text from CVE List
Affected versions 2
- vllmaffected: all versions before 0.31.0CVE List
- vllmunaffected: 0.31.0CVE List