CVE-2026-86288: ModelCloud GPTQModel Triton dequantization kernel tritonv2.py out-of-bounds
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
Remediation
Recommended actions to resolve this vulnerability, in priority order.
- Upgrade
Upgrade
ModelCloud GPTQModelto a version that resolves this vulnerability.Fixed in 7.3.0Patch 877c732f7d7dccd56a729844c6a5bd20f3aa8bb1
Event History
Frequently Asked Questions
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.
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.
Is public exploit information available?
Yes. The exploit has been publicly disclosed and may be used.
What is the remediation?
Upgrade GPTQModel to version 7.3.0. The associated patch is 877c732f7d7dccd56a729844c6a5bd20f3aa8bb1.