CVE-2026-69147
MEDIUMDescription
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.
How to fix
No published remediation has been found for this vulnerability's affected products yet.
Mitigation guidance may be in the linked vendor advisories in the References section below.
TridentStack Control tracks known vulnerabilities across your Windows, macOS, and Linux fleet and shows the fix as soon as one is published. See how it works
CVSS v3 Vector
Exploitability
Impact
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Exploit Intelligence
Low risk: more likely to be exploited than 39% of all known CVEs.
References
Related Vulnerabilities
Other CWE-400 (Resource Exhaustion) vulnerabilities, ordered by exploit likelihood. View all
| CVE | Severity | CVSS | EPSS | Exploited | Fix |
|---|---|---|---|---|---|
| CVE-2023-44487 | High | 7.5 | 100% | KEV | Fix |
| CVE-2021-44228 | Critical | 10.0 | 100% | KEV + Ransom | Fix |
| CVE-2011-3192 | High | 7.8 | 99% | - | Fix |
| CVE-2019-11478 | Medium | 5.3 | 95% | - | Fix |
| CVE-2023-21547 | High | 7.5 | 89% | - | Fix |
| CVE-2018-1000115 | High | 7.5 | 88% | - | Fix |
Common questions
How do I fix CVE-2026-69147?
No published fix for CVE-2026-69147 has been found yet. Check the linked vendor advisories for guidance as it becomes available.
Is CVE-2026-69147 being actively exploited?
Not that we know of. CVE-2026-69147 is not in the CISA Known Exploited Vulnerabilities catalog. Its EPSS score of 0.46% is the estimated probability that it will be exploited in the next 30 days. That is higher than 39% of all scored CVEs.
How severe is CVE-2026-69147?
CVE-2026-69147 has a CVSS v3 base score of 6.5, rated medium. CVSS rates the technical impact if the vulnerability is exploited, not how likely that is, so weigh it alongside the exploit-prediction score when you decide what to patch first.
Embed a live status badge for CVE-2026-69147
Markdown
[](https://tridentstack.com/cve/CVE-2026-69147)HTML
<a href="https://tridentstack.com/cve/CVE-2026-69147"><img src="https://tridentstack.com/cve/badge/CVE-2026-69147.svg" alt="CVE-2026-69147"></a>Find and fix vulnerabilities across your fleet
TridentStack Control continuously scans your Windows, macOS, and Linux fleet for known vulnerabilities, prioritizes them by severity and active exploitation, and patches them automatically.
This product uses NVD data but is not endorsed or certified by the NVD. EPSS scores courtesy of FIRST.org (https://www.first.org/epss). Source: CISA KEV Catalog. Data as of 2026-09-16.