{
  "affected": [
    {
      "ranges": [
        {
          "database_specific": {
            "cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
            "extracted_events": [
              {
                "introduced": "0.18.0"
              },
              {
                "fixed": "0.20.0"
              }
            ],
            "source": [
              "AFFECTED_FIELD",
              "CPE_RANGE"
            ]
          },
          "events": [
            {
              "introduced": "bcf2be96120005e9aea171927f85055a6a5c0cf6"
            },
            {
              "fixed": "88d34c6409e9fb3c7b8ca0c04756f061d2099eb1"
            }
          ],
          "repo": "https://github.com/vllm-project/vllm",
          "type": "GIT"
        }
      ]
    }
  ],
  "aliases": [
    "GHSA-83vm-p52w-f9pw"
  ],
  "database_specific": {
    "cna_assigner": "GitHub_M",
    "cwe_ids": [
      "CWE-131",
      "CWE-704"
    ],
    "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/44xxx/CVE-2026-44223.json"
  },
  "details": "vLLM is an inference and serving engine for large language models (LLMs). From 0.18.0 to before 0.20.0, the extract_hidden_states speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The crash is triggered when any request in the batch uses sampling penalty parameters (repetition_penalty, frequency_penalty, or presence_penalty). A single request with a penalty parameter (e.g., \"repetition_penalty\": 1.1) is sufficient to crash the server. This vulnerability is fixed in 0.20.0.",
  "id": "CVE-2026-44223",
  "modified": "2026-07-08T05:36:12.980757105Z",
  "published": "2026-05-12T19:58:40.862Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/44xxx/CVE-2026-44223.json"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-44223"
    },
    {
      "type": "FIX",
      "url": "https://github.com/vllm-project/vllm/pull/38610"
    }
  ],
  "schema_version": "1.7.5",
  "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: extract_hidden_states speculative decoding crashes server on any request with penalty parameters"
}