Skip to content
Fencer Intel
medium 6.5

CVE-2026-69147 json

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

published last mo. modified last mo. also EUVD-2026-80935 , GHSA-8pw2-6jv3-mj5j , PYSEC-2026-4178

cvss
6.5
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.6%
EPSS 0.6% chance of exploitation in 30 days, percentile 48%
public exploits
0
none known

Summary

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.

Patch / fix

  • pypi vllm 0.28.0
  • vllm-project vllm 0.28.0
  • vllm vllm 0.28.0

Is CVE-2026-69147 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2026-69147 updated cvss 6.5

vllm: vLLM: GPU memory exhaustion via PyNvVideoCodec decode bypass

  • Red Hat AI Inference Server rhaii/vllm-tpu-rhel9, rhaiis/vllm-cpu-rhel9, rhaiis/vllm-tpu-rhel9, rhaiis/vllm-cuda-rhel9, rhaiis/vllm-rocm-rhel9, rhaii/vllm-neuron-rhel9, +2 more Red Hat Enterprise Linux AI (RHEL AI) 3 rhelai3/bootc-gaudi-rhel9 Red Hat OpenShift AI (RHOAI) rhoai/odh-vllm-gaudi-rhel9, rhoai/odh-kserve-agent-rhel9, rhoai/odh-kserve-router-rhel9, rhoai/odh-llm-d-kv-cache-rhel9, rhoai/odh-kserve-controller-rhel9, rhoai/odh-th-torch-cuda-py312-rhel9, +1 more
    affected: workaround, no fix available “Fix deferred”
  • Red Hat AI Inference Server 3.5 rhaii/vllm-cpu-rhel9 1791473614, rhaii/vllm-cuda-rhel9 1791473631, rhaii/vllm-rocm-rhel9 1791425869, rhaii/vllm-gaudi-rhel9 1791427182, rhaii/vllm-spyre-rhel9 1791818357
    fixed: vendor fix RHSA-2026:82415
  • Red Hat Enterprise Linux AI 3.5 rhelai3/bootc-cuda-rhel9 1793135861, rhelai3/bootc-rocm-rhel9 1793135863, rhelai3/bootc-aws-cuda-rhel9 1793194817, rhelai3/bootc-gcp-cuda-rhel9 1793194815, rhelai3/disk-image-cuda-rhel9 1793206758, rhelai3/bootc-azure-cuda-rhel9 1793194815, +1 more
    fixed: vendor fix RHSA-2026:92452

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
Proof of concept is public
Automatable
no
Technical impact
partial
Assessed
last mo.

Exploit prediction

0.58% chance of exploitation in the next 30 days, higher than 48% of all scored CVEs (FIRST EPSS, 2026-11-11).

Exploits and checks

  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3-mj5j referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 3.1 6.5 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
GitHub 3.1 6.5 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
OSV 3.1 6.5 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

Affected packages

ecosystem package affected fixed in
pypi vllm
<0.28.0
0.28.0

Affected products

  • vllm-project vllm

Classification

Weakness
  • CWE-400 Uncontrolled Resource Consumption
  • CWE-770 Allocation of Resources Without Limits or Throttling

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.