---
id: CVE-2026-100652
title: >-
  vLLM versions 0.22.0 through 0.23.0 fail to validate stop_token_ids against
  vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary
  token IDs to reach MinTokensLogitsProcessor
summary: >-
  vLLM versions 0.22.0 through 0.23.0 fail to validate stop_token_ids against
  vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary
  token IDs to reach MinTokensLogitsProcessor. Attackers can submit requests
  with min…
severity: medium
cvss: 5.9
cvssVector: 'CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H'
cwe:
  - CWE-20
vendor: vllm-project
product: vllm
affected:
  - vllm >= 0.22.0 < 0.24.0
published: '2026-09-26'
updated: '2026-09-26'
sourceUpdated: '2026-09-26T14:16:47.810'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-100652'
references:
  - url: >-
      https://github.com/vllm-project/vllm/security/advisories/GHSA-qff2-492f-9fm4
    label: disclosure@vulncheck.com
  - url: >-
      https://www.vulncheck.com/advisories/vllm-0.22.0-through-0.23.0-denial-of-service-via-stop-token-ids
    label: disclosure@vulncheck.com
tags:
  - nvd
  - cve.org
ingestedAt: '2026-09-26T13:33:20.918Z'
---

## Overview

vLLM versions 0.22.0 through 0.23.0 fail to validate stop_token_ids against vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary token IDs to reach MinTokensLogitsProcessor. Attackers can submit requests with min_tokens greater than zero and out-of-vocabulary stop_token_ids to trigger CUDA tensor indexing failures that leave EngineCore in a fatal state requiring service restart.

## Remediation

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