{
  "affected": [
    {
      "ranges": [
        {
          "database_specific": {
            "extracted_events": [
              {
                "cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
                "range": [
                  {
                    "introduced": "0.31.0"
                  },
                  {
                    "fixed": "0.32.0"
                  }
                ],
                "source": "CPE_RANGE"
              },
              {
                "range": [
                  {
                    "fixed": "3d52578e13454de0bb8352cac988347cdcc89928"
                  }
                ],
                "source": "REFERENCES_COMMIT"
              },
              {
                "original_tag": "v0.32.0",
                "range": [
                  {
                    "fixed": "5df63a7203cdb9328d824a27b682e77c7b9928be"
                  }
                ],
                "source": "REFERENCES_TAG"
              }
            ]
          },
          "events": [
            {
              "introduced": "db9527a46873454610df6dbedf79a36d6bf1a7f6"
            },
            {
              "fixed": "5df63a7203cdb9328d824a27b682e77c7b9928be"
            },
            {
              "fixed": "3d52578e13454de0bb8352cac988347cdcc89928"
            }
          ],
          "repo": "https://github.com/vllm-project/vllm",
          "type": "GIT"
        }
      ]
    }
  ],
  "aliases": [
    "GHSA-8397-8qf6-f2gm"
  ],
  "database_specific": {
    "cna_assigner": "GitHub_M",
    "cwe_ids": [
      "CWE-770"
    ],
    "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/115xxx/CVE-2026-115913.json"
  },
  "details": "vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the Phi-4 multimodal audio encoder in phi4mm_audio.py and phi4mm_utils.py uses eager attention by default, allowing a remote client to submit one legal long audio clip that causes MultiHeadedAttention.forward_attention to materialize and retain full attention matrices in self.attn. The scaled dot-product attention branch does not materialize these matrices. The resulting quadratic GPU-memory use can cause an out-of-memory condition and terminate EngineCore for all users. This issue is fixed in version 0.32.0.",
  "id": "CVE-2026-115913",
  "modified": "2026-11-11T10:31:02.800246088Z",
  "published": "2026-10-26T16:56:59.817Z",
  "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-2026-115913.json"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8397-8qf6-f2gm"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-115913"
    },
    {
      "type": "FIX",
      "url": "https://github.com/vllm-project/vllm/commit/3d52578e13454de0bb8352cac988347cdcc89928"
    },
    {
      "type": "FIX",
      "url": "https://github.com/vllm-project/vllm/pull/60614"
    }
  ],
  "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: Phi-4 multimodal audio encoder materializes and retains full attention matrices: a single max-length audio OOM-crashes the vLLM engine"
}