{"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": "2026-11-02T17:48:14.216Z"}, "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"}}, "adp": [{"metrics": [{"other": {"type": "ssvc", "content": {"timestamp": "2026-11-02T17:48:03.108418Z", "id": "CVE-2026-115913", "options": [{"Exploitation": "none"}, {"Automatable": "no"}, {"Technical Impact": "partial"}], "role": "CISA Coordinator", "version": "2.0.3"}}}], "title": "CISA ADP Vulnrichment", "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2026-11-02T17:48:14.216Z"}}]}}

{"dataType": "CVE_RECORD", "containers": {"adp": [{"title": "CISA ADP Vulnrichment", "metrics": [{"other": {"type": "ssvc", "content": {"id": "CVE-2026-115913", "role": "CISA Coordinator", "options": [{"Exploitation": "none"}, {"Automatable": "no"}, {"Technical Impact": "partial"}], "version": "2.0.3", "timestamp": "2026-11-02T17:48:03.108418Z"}}}], "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2026-11-02T17:48:10.035Z"}}], "cna": {"title": "vLLM: Phi-4 multimodal audio encoder materializes and retains full attention matrices: a single max-length audio OOM-crashes the vLLM engine", "source": {"advisory": "GHSA-8397-8qf6-f2gm", "discovery": "UNKNOWN"}, "metrics": [{"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": "< 0.32.0"}]}], "references": [{"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8397-8qf6-f2gm", "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8397-8qf6-f2gm", "tags": ["x_refsource_CONFIRM"]}, {"url": "https://github.com/vllm-project/vllm/pull/60614", "name": "https://github.com/vllm-project/vllm/pull/60614", "tags": ["x_refsource_MISC"]}, {"url": "https://github.com/vllm-project/vllm/commit/3d52578e13454de0bb8352cac988347cdcc89928", "name": "https://github.com/vllm-project/vllm/commit/3d52578e13454de0bb8352cac988347cdcc89928", "tags": ["x_refsource_MISC"]}, {"url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0", "name": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0", "tags": ["x_refsource_MISC"]}], "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."}], "problemTypes": [{"descriptions": [{"lang": "en", "type": "CWE", "cweId": "CWE-770", "description": "CWE-770: Allocation of Resources Without Limits or Throttling"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2026-10-26T16:56:59.817Z"}}}, "cveMetadata": {"cveId": "CVE-2026-115913", "state": "PUBLISHED", "dateUpdated": "2026-11-02T17:48:14.216Z", "dateReserved": "2026-10-23T20:21:45.107Z", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "datePublished": "2026-10-26T16:56:59.817Z", "assignerShortName": "GitHub_M"}, "dataVersion": "5.2"}

{"affected": [{"affectedData": [{"product": "vllm", "vendor": "vllm-project", "versions": [{"status": "affected", "version": "< 0.32.0"}]}], "source": "security-advisories@github.com"}], "configurations": [{"nodes": [{"cpeMatch": [{"criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*", "matchCriteriaId": "50F36C60-8E0D-429B-9425-BFA2A4F71448", "versionEndExcluding": "0.32.0", "versionStartIncluding": "0.31.0", "vulnerable": true}], "negate": false, "operator": "OR"}]}], "cveTags": [], "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."}], "id": "CVE-2026-115913", "lastModified": "2026-11-02T18:18:38.870", "metrics": {"cvssMetricV31": [{"cvssData": {"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"}, "exploitabilityScore": 2.8, "impactScore": 3.6, "source": "security-advisories@github.com", "type": "Secondary"}], "ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-115913", "options": [{"exploitation": "none"}, {"automatable": "no"}, {"technicalImpact": "partial"}], "role": "CISA Coordinator", "timestamp": "2026-11-02T17:48:03.108418Z", "version": "2.0.3"}}]}, "published": "2026-10-26T17:17:19.053", "references": [{"source": "security-advisories@github.com", "tags": ["Patch"], "url": "https://github.com/vllm-project/vllm/commit/3d52578e13454de0bb8352cac988347cdcc89928"}, {"source": "security-advisories@github.com", "tags": ["Patch"], "url": "https://github.com/vllm-project/vllm/pull/60614"}, {"source": "security-advisories@github.com", "tags": ["Release Notes"], "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"}, {"source": "security-advisories@github.com", "tags": ["Exploit", "Patch", "Vendor Advisory"], "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8397-8qf6-f2gm"}], "sourceIdentifier": "security-advisories@github.com", "vulnStatus": "Analyzed", "weaknesses": [{"description": [{"lang": "en", "value": "CWE-770"}], "source": "security-advisories@github.com", "type": "Secondary"}]}

{}