CVE-2026-86288: ModelCloud GPTQModel Triton dequantization kernel tritonv2.py out-of-bounds

Published Sep 7, 2026
·
Updated

A vulnerability has been found in ModelCloud GPTQModel up to 7.2.0. This vulnerability affects unknown code of the file gptqmodel/nnmodules/qlinear/tritonv2.py of the component Triton dequantization kernel. Such manipulation of the argument gidx leads to out-of-bounds read. The attack can be executed remotely. The exploit has been disclosed to the public and may be used. Upgrading to version 7.3.0 is able to resolve this issue. The name of the patch is 877c732f7d7dccd56a729844c6a5bd20f3aa8bb1. Upgrading the affected component is recommended.

Affected Software

1 affected component
ModelCloud GPTQModel<=7.2.0

Remediation

Recommended actions to resolve this vulnerability, in priority order.

  1. Upgrade

    Upgrade ModelCloud GPTQModel to a version that resolves this vulnerability.

    Fixed in 7.3.0Patch 877c732f7d7dccd56a729844c6a5bd20f3aa8bb1

Event History

Sep 7, 2026
CVE Published
via MITRE·08:30 AM
Data Sourced
via MITRE·08:30 AM
DescriptionSeverityWeakness

Frequently Asked Questions

1

Which deployments are affected?

ModelCloud GPTQModel versions up to and including 7.2.0 are affected when using the Triton dequantization kernel code in gptqmodel/nn_modules/qlinear/tritonv2.py.

2

What does an attacker need to exploit this issue?

The issue can be exploited remotely by manipulating the g_idx argument. No privileges are required, but user interaction is required according to the provided severity vector.

3

Is public exploit information available?

Yes. The exploit has been publicly disclosed and may be used.

4

What is the remediation?

Upgrade GPTQModel to version 7.3.0. The associated patch is 877c732f7d7dccd56a729844c6a5bd20f3aa8bb1.

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