{
  "affected": [
    {
      "ranges": [
        {
          "database_specific": {
            "extracted_events": [
              {
                "cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
                "range": [
                  {
                    "introduced": "0.19.0"
                  },
                  {
                    "fixed": "0.32.0"
                  }
                ],
                "source": "CPE_RANGE"
              },
              {
                "range": [
                  {
                    "fixed": "cff08b461e086523cee8bba5bd3c66d302625134"
                  }
                ],
                "source": "REFERENCES_COMMIT"
              },
              {
                "original_tag": "v0.32.0",
                "range": [
                  {
                    "fixed": "5df63a7203cdb9328d824a27b682e77c7b9928be"
                  }
                ],
                "source": "REFERENCES_TAG"
              }
            ]
          },
          "events": [
            {
              "introduced": "2a69949bdadf0e8942b7a1619b229cb475beef20"
            },
            {
              "fixed": "5df63a7203cdb9328d824a27b682e77c7b9928be"
            },
            {
              "fixed": "cff08b461e086523cee8bba5bd3c66d302625134"
            }
          ],
          "repo": "https://github.com/vllm-project/vllm",
          "type": "GIT"
        }
      ]
    }
  ],
  "aliases": [
    "GHSA-542m-9234-8gvf"
  ],
  "database_specific": {
    "cna_assigner": "GitHub_M",
    "cwe_ids": [
      "CWE-400",
      "CWE-770",
      "CWE-834"
    ],
    "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/115xxx/CVE-2026-115911.json"
  },
  "details": "vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authenticated callers can supply a request chat template when no server-side --chat-template is configured, or a malicious model repository can provide a template that is compiled and rendered by tokenizer.apply_chat_template() without a wall-clock timeout, output-size limit, or iteration bound. Rendering runs in a ThreadPoolExecutor with one worker by default, so a nonterminating render can block /v1/responses and other chat-template users after the request ends, while an output-expanding render can exhaust server memory. Harmony models are not affected because they do not use this Jinja path. This issue is fixed in version 0.32.0.",
  "id": "CVE-2026-115911",
  "modified": "2026-11-01T02:30:57.443898758Z",
  "published": "2026-10-26T16:47:59.377Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/115xxx/CVE-2026-115911.json"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-542m-9234-8gvf"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-115911"
    },
    {
      "type": "FIX",
      "url": "https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134"
    },
    {
      "type": "FIX",
      "url": "https://github.com/vllm-project/vllm/pull/50300"
    }
  ],
  "schema_version": "1.9.2",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool"
}