CVE-2026-69147

vLLM is an inference and serving engine for large language models. Prior to 0.28.0, request bodies for Chat Completions and Responses can set media_io_kwargs.video.video_backend to pynvvideocodec, and MediaConnector.fetch_video forwards that choice to VideoMediaIO even when startup configuration selected a software decoder. The engine's _reserve_mm_ipc_gpu_memory logic budgets decoder memory only from static configuration, so the request-selected VIDEO_LOADER_REGISTRY backend can create a CUDA context, decoder surfaces, and decoded-frame allocations that were not removed from the engine's KV-cache budget. An attacker able to submit video requests to a video-capable GPU deployment with PyNvVideoCodec installed can exhaust shared GPU memory, causing request failures, worker crashes, or denial of service. The first release containing the fix is version 0.28.0.

CVSS v3 6.5 MEDIUM

6.5^/10

CVSS v3 : MEDIUM

Vector :

Exploitability : 2.8 / Impact : 3.6

Attack Vector NETWORK

Attack Complexity LOW

Privileges Required LOW

User Interaction NONE

Confidentiality Impact NONE

Integrity Impact NONE

Availability Impact HIGH

Scope UNCHANGED

References

Link	Resource
https://github.com/vllm-project/vllm/commit/283893c72292ede38d277e3cd2b9b64c3e4f1dda
https://github.com/vllm-project/vllm/commit/ba22152096b2484faa3579624a253d54804d876d
https://github.com/vllm-project/vllm/pull/47259
https://github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3-mj5j
https://github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3-mj5j

Configurations

No configuration.

History

16 Sep 2026, 19:17

Type	Values Removed	Values Added
References	~~() https://github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3-mj5j -~~	() https://github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3-mj5j -

16 Sep 2026, 18:17

Type	Values Removed	Values Added
New CVE

Information

Published : 2026-09-16 18:17

Updated : 2026-09-16 19:17

NVD link : CVE-2026-69147

Mitre link : CVE-2026-69147

CVE.ORG link : CVE-2026-69147

JSON object : View

Products Affected

No product.

CWE

CWE-400

Uncontrolled Resource Consumption

CWE-770

Allocation of Resources Without Limits or Throttling

{"id": "CVE-2026-69147", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-69147", "role": "CISA Coordinator", "options": [{"exploitation": "poc"}, {"automatable": "no"}, {"technicalImpact": "partial"}], "version": "2.0.3", "timestamp": "2026-09-16T18:37:08.090589Z"}}], "cvssMetricV31": [{"type": "Secondary", "source": "security-advisories@github.com", "cvssData": {"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"}, "impactScore": 3.6, "exploitabilityScore": 2.8}]}, "affected": [{"source": "security-advisories@github.com", "affectedData": [{"vendor": "vllm-project", "product": "vllm", "versions": [{"status": "affected", "version": "< 0.28.0"}]}]}], "published": "2026-09-16T18:17:11.770", "references": [{"url": "https://github.com/vllm-project/vllm/commit/283893c72292ede38d277e3cd2b9b64c3e4f1dda", "source": "security-advisories@github.com"}, {"url": "https://github.com/vllm-project/vllm/commit/ba22152096b2484faa3579624a253d54804d876d", "source": "security-advisories@github.com"}, {"url": "https://github.com/vllm-project/vllm/pull/47259", "source": "security-advisories@github.com"}, {"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3-mj5j", "source": "security-advisories@github.com"}, {"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3-mj5j", "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0"}], "vulnStatus": "Received", "weaknesses": [{"type": "Secondary", "source": "security-advisories@github.com", "description": [{"lang": "en", "value": "CWE-400"}, {"lang": "en", "value": "CWE-770"}]}], "descriptions": [{"lang": "en", "value": "vLLM is an inference and serving engine for large language models. Prior to 0.28.0, request bodies for Chat Completions and Responses can set media_io_kwargs.video.video_backend to pynvvideocodec, and MediaConnector.fetch_video forwards that choice to VideoMediaIO even when startup configuration selected a software decoder. The engine's _reserve_mm_ipc_gpu_memory logic budgets decoder memory only from static configuration, so the request-selected VIDEO_LOADER_REGISTRY backend can create a CUDA context, decoder surfaces, and decoded-frame allocations that were not removed from the engine's KV-cache budget. An attacker able to submit video requests to a video-capable GPU deployment with PyNvVideoCodec installed can exhaust shared GPU memory, causing request failures, worker crashes, or denial of service. The first release containing the fix is version 0.28.0."}], "lastModified": "2026-09-16T19:17:26.113", "sourceIdentifier": "security-advisories@github.com"}