---
id: CVE-2026-114051
title: vLLM before 0.31.0 Denial of Service via min_tokens in /inference/v1/generate
summary: >-
  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. Unauthe…
severity: high
cvss: 7.5
cvssVector: 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H'
cvssSource: cna
cwe:
  - CWE-248
vendor: vllm-project
product: vllm
affected:
  - vllm < 0.31.0
published: '2026-10-21'
updated: '2026-10-21'
sourceUpdated: '2026-10-21T00:36:28.373Z'
source: CVEORG
sourceUrl: 'https://www.cve.org/CVERecord?id=CVE-2026-114051'
references:
  - url: >-
      https://github.com/vllm-project/vllm/security/advisories/GHSA-4xqp-c3mv-qff7
    label: GitHub Security Advisory (GHSA-4xqp-c3mv-qff7)
  - url: >-
      https://www.vulncheck.com/advisories/vllm-before-0.31.0-denial-of-service-via-min-tokens-in-inference-v1-generate
    label: >-
      VulnCheck Advisory: vLLM before 0.31.0 Denial of Service via min_tokens in
      /inference/v1/generate
tags:
  - cve.org
ingestedAt: '2026-10-21T01:37:08.043Z'
---

## Overview

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.

## Affected

- `vllm < 0.31.0`

## Remediation

Refer to the linked advisories for vendor-supplied fixes and affected version ranges.