CVE-2026-126394: vLLM 0.30.0 before 0.31.0 Resource Exhaustion via OpenPangu Video Backend num_frames

Published Nov 13, 2026
·
Updated

vLLM 0.30.0 before 0.31.0 contains a resource exhaustion vulnerability in OpenCVDynamicOpenPanguVideoBackend, which uses request-controlled numframes without an effective ceiling. Unauthenticated attackers can send /v1/chat/completions or /tokenize requests selecting the openpangu videobackend with a huge numframes, forcing np.linspace allocations and CPU work that OOM-kill the API server.

Affected Software

1 affected component
pypi/vllm>=0.30.0<0.31.0

Event History

Nov 13, 2026
CVE Published
via MITRE·09:35 AM
Data Sourced
via MITRE·09:35 AM
DescriptionSeverityWeakness
Data Sourced
via NVD·10:17 AM
DescriptionSeverityWeakness

Frequently Asked Questions

1

Which deployments are exposed to unauthenticated exploitation?

API servers that expose /v1/chat/completions or /tokenize and allow requests to select the openpangu video_backend are exposed. No credentials or user interaction are required.

2

What does an attacker need to send?

An attacker needs to submit a request using the openpangu video backend with a very large num_frames value. The request-controlled value can trigger np.linspace allocations and CPU work.

3

What is the practical impact on an affected server?

The API server can consume sufficient memory and CPU resources to be OOM-killed, causing denial of service. The provided information identifies no confidentiality or integrity impact.

4

What versions are affected?

The affected range is vLLM 0.30.0 before 0.31.0. Version 0.31.0 is not included in the stated affected range.

Contact

SecAlerts Pty Ltd.
132 Wickham Terrace
Fortitude Valley,
QLD 4006, Australia
info@secalerts.co
By using SecAlerts services, you agree to our services end-user license agreement. This website is safeguarded by reCAPTCHA and governed by the Google Privacy Policy and Terms of Service. All names, logos, and brands of products are owned by their respective owners, and any usage of these names, logos, and brands for identification purposes only does not imply endorsement. If you possess any content that requires removal, please get in touch with us.
© 2026 SecAlerts Pty Ltd.
ABN: 70 645 966 203, ACN: 645 966 203