Buffer overflow in Modelcloud Gptqmodel
CVE-2026-86288
A vulnerability has been found in ModelCloud GPTQModel up to 7.2.0. This vulnerability affects unknown code of the file gptqmodel/nn_modules/qlinear/tritonv2.py of the component Triton dequantization kernel. Such manipulation of the argument g_idx 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.
Vulnerability class: Buffer Overflow
CVSS v3 metric
CVSS v3 base score 6.3 (Medium). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:L/A:L.
Affected products
- Modelcloud Gptqmodel — versions 7.0, 7.1, 7.2.0
Weakness classification (CWE)
References
- cna@vuldb.com (technical-description, vdb-entry)
- cna@vuldb.com (signature, permissions-required)
- cna@vuldb.com (third-party-advisory)
- cna@vuldb.com (third-party-advisory)
- cna@vuldb.com (issue-tracking, exploit)
- cna@vuldb.com (issue-tracking, patch)
- cna@vuldb.com (patch)
- cna@vuldb.com (patch)
- cna@vuldb.com (product)
Frequently asked questions
- What is CVE-2026-86288?
- CVE-2026-86288 is a medium-severity vulnerability in Modelcloud Gptqmodel, classified under Improper Restriction of Operations within the Bounds of a Memory Buffer. CVSS score: 6.3/10. Published 2026-09-07.
- How severe is CVE-2026-86288?
- Medium severity. CVSS v3 base score is 6.3 out of 10.