vLLM 0.20.1 before 0.29.0 DoS and GPU Out-of-Bounds Write via stop_token_ids

{
  "id": "08fda4bc820fd9c5378dd479b20c829435b9fca52977f58e01ef93fa5f59b01a",
  "url": "https://www.cve.org/CVERecord?id=CVE-2026-116181",
  "method": "structured",
  "payload": {
    "kind": "advisory",
    "title": "vLLM 0.20.1 before 0.29.0 DoS and GPU Out-of-Bounds Write via stop_token_ids",
    "summary": "vLLM from 0.20.1 before 0.29.0 contains an improper input validation vulnerability that allows remote attackers to crash the engine by supplying out-of-vocabulary stop_token_ids. Attackers can send OpenAI chat, completion, generate, or batch requests with invalid IDs to terminate the engine or write outside the V2 runner's logits buffer.",
    "evidence": "cve:CVE-2026-116181",
    "products": [
      {
        "name": {
          "value": "vllm",
          "evidence": "/containers/cna/affected/0/product"
        },
        "prerequisites": [],
        "fixed_versions": [],
        "affected_versions": []
      }
    ],
    "severity": "high",
    "structured": {
      "id": "CVE-2026-116181",
      "aliases": [
        "CVE-2026-116181"
      ],
      "metrics": [
        {
          "format": "CVSS",
          "cvssV4_0": {
            "version": "4.0",
            "baseScore": 7.1,
            "attackVector": "NETWORK",
            "baseSeverity": "HIGH",
            "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N",
            "userInteraction": "NONE",
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "privilegesRequired": "LOW",
            "subIntegrityImpact": "NONE",
            "vulnIntegrityImpact": "NONE",
            "subAvailabilityImpact": "NONE",
            "vulnAvailabilityImpact": "HIGH",
            "subConfidentialityImpact": "NONE",
            "vulnConfidentialityImpact": "NONE"
          }
        },
        {
          "format": "CVSS",
          "cvssV3_1": {
            "scope": "UNCHANGED",
            "version": "3.1",
            "baseScore": 6.5,
            "attackVector": "NETWORK",
            "baseSeverity": "MEDIUM",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
            "integrityImpact": "NONE",
            "userInteraction": "NONE",
            "attackComplexity": "LOW",
            "availabilityImpact": "HIGH",
            "privilegesRequired": "LOW",
            "confidentialityImpact": "NONE"
          }
        }
      ],
      "affected": [
        {
          "vendor": "vllm-project",
          "product": "vllm",
          "versions": [
            {
              "status": "affected",
              "version": "0.20.1",
              "lessThan": "0.29.0",
              "versionType": "semver"
            },
            {
              "status": "unaffected",
              "version": "0.29.0",
              "versionType": "semver"
            }
          ],
          "packageURL": "pkg:pypi/vllm",
          "defaultStatus": "unaffected"
        }
      ],
      "modified": "2026-10-25T13:20:19.874Z",
      "provider": "cve",
      "references": [
        "https://github.com/vllm-project/vllm/security/advisories/GHSA-w9r6-29q4-pvpr",
        "https://www.vulncheck.com/advisories/vllm-0.20.1-before-0.29.0-dos-and-gpu-out-of-bounds-write-via-stop-token-ids"
      ],
      "provider_metadata": {
        "cna": {
          "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
          "shortName": "VulnCheck",
          "dateUpdated": "2026-10-25T13:20:19.874Z"
        }
      }
    },
    "related_cves": [
      {
        "value": "CVE-2026-116181",
        "evidence": "/cveMetadata/cveId"
      }
    ],
    "security_relevant": true,
    "severity_evidence": "/containers/cna/metrics"
  },
  "source_id": "core-cve",
  "document_id": 146789,
  "published_at": "2026-10-25T13:20:19.874+00:00"
}