vLLM: Request-selected PyNvVideoCodec GPU decode bypasses static VRAM reservation

MITRE NVD CVE.ORG JSON API

Summary

CVECVE-2026-69147
StatePUBLISHED
AssignerGitHub_M
Source PriorityCVE Program / NVD first with legacy fallback
Published2026-09-16 18:17:11 UTC
Updated2026-09-30 17:43:24 UTC
DescriptionvLLM 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.

Risk And Classification

Primary CVSS: v3.1 6.5 MEDIUM from [email protected]

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

EPSS: 0.005480000 probability, percentile 0.439070000 (date 2026-10-02)

Problem Types: CWE-400 | CWE-770 | CWE-400 CWE-400: Uncontrolled Resource Consumption | CWE-770 CWE-770: Allocation of Resources Without Limits or Throttling

VersionSourceTypeScoreSeverityVector
3.1[email protected]Secondary6.5MEDIUMCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
3.1CNADECLARED6.5MEDIUMCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

CVSS v3.1 Breakdown

Attack Vector
Network
Attack Complexity
Low
Privileges Required
Low
User Interaction
None
Scope
Unchanged
Confidentiality
None
Integrity
None
Availability
High

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

Vendor Declared Affected Products

SourceVendorProductVersionPlatforms
CNA Vllm-project Vllm affected < 0.28.0 Not specified

References

ReferenceSourceLinkTags
github.com/vllm-project/vllm/commit/283893c72292ede38d277e3cd2b9b64c3e4f... [email protected] github.com
github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3-mj5j 134c704f-9b21-4f2e-91b3-4a467353bcc0 github.com
github.com/vllm-project/vllm/pull/47259 [email protected] github.com
github.com/vllm-project/vllm/commit/ba22152096b2484faa3579624a253d54804d... [email protected] github.com
CVE Program record CVE.ORG www.cve.org canonical
NVD vulnerability detail NVD nvd.nist.gov canonical, analysis

© CVE.report 2026

Use of this information constitutes acceptance for use in an AS IS condition. There are NO warranties, implied or otherwise, with regard to this information or its use. Any use of this information is at the user's risk. It is the responsibility of user to evaluate the accuracy, completeness or usefulness of any information, opinion, advice or other content. EACH USER WILL BE SOLELY RESPONSIBLE FOR ANY consequences of his or her direct or indirect use of this web site. ALL WARRANTIES OF ANY KIND ARE EXPRESSLY DISCLAIMED. This site will NOT BE LIABLE FOR ANY DIRECT, INDIRECT or any other kind of loss.

CVE, CWE, and OVAL are registred trademarks of The MITRE Corporation and the authoritative source of CVE content is MITRE's CVE web site. This site includes MITRE data granted under the following license.

Free CVE JSON API cve.report/api

CVE.report and Source URL Uptime Status status.cve.report