{
    "dataType": "CVE_RECORD",
    "dataVersion": "5.2",
    "cveMetadata": {
        "cveId": "CVE-2026-115913",
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "state": "PUBLISHED",
        "assignerShortName": "GitHub_M",
        "dateReserved": "2026-10-23T20:21:45.107Z",
        "datePublished": "2026-10-26T16:56:59.817Z",
        "dateUpdated": "2026-10-26T16:56:59.817Z"
    },
    "containers": {
        "cna": {
            "title": "vLLM: Phi-4 multimodal audio encoder materializes and retains full attention matrices: a single max-length audio OOM-crashes the vLLM engine",
            "problemTypes": [
                {
                    "descriptions": [
                        {
                            "cweId": "CWE-770",
                            "lang": "en",
                            "description": "CWE-770: Allocation of Resources Without Limits or Throttling",
                            "type": "CWE"
                        }
                    ]
                }
            ],
            "metrics": [
                {
                    "cvssV3_1": {
                        "attackComplexity": "LOW",
                        "attackVector": "NETWORK",
                        "availabilityImpact": "HIGH",
                        "baseScore": 6.5,
                        "baseSeverity": "MEDIUM",
                        "confidentialityImpact": "NONE",
                        "integrityImpact": "NONE",
                        "privilegesRequired": "LOW",
                        "scope": "UNCHANGED",
                        "userInteraction": "NONE",
                        "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
                        "version": "3.1"
                    }
                }
            ],
            "references": [
                {
                    "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8397-8qf6-f2gm",
                    "tags": [
                        "x_refsource_CONFIRM"
                    ],
                    "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8397-8qf6-f2gm"
                },
                {
                    "name": "https://github.com/vllm-project/vllm/pull/60614",
                    "tags": [
                        "x_refsource_MISC"
                    ],
                    "url": "https://github.com/vllm-project/vllm/pull/60614"
                },
                {
                    "name": "https://github.com/vllm-project/vllm/commit/3d52578e13454de0bb8352cac988347cdcc89928",
                    "tags": [
                        "x_refsource_MISC"
                    ],
                    "url": "https://github.com/vllm-project/vllm/commit/3d52578e13454de0bb8352cac988347cdcc89928"
                },
                {
                    "name": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0",
                    "tags": [
                        "x_refsource_MISC"
                    ],
                    "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
                }
            ],
            "affected": [
                {
                    "vendor": "vllm-project",
                    "product": "vllm",
                    "versions": [
                        {
                            "version": "< 0.32.0",
                            "status": "affected"
                        }
                    ]
                }
            ],
            "providerMetadata": {
                "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
                "shortName": "GitHub_M",
                "dateUpdated": "2026-10-26T16:56:59.817Z"
            },
            "descriptions": [
                {
                    "lang": "en",
                    "value": "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."
                }
            ],
            "source": {
                "advisory": "GHSA-8397-8qf6-f2gm",
                "discovery": "UNKNOWN"
            }
        }
    }
}