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.
https://vuldb.com/vuln/399447/cti
https://vuldb.com/submit/906135
https://vuldb.com/cve/CVE-2026-86288
https://github.com/ModelCloud/GPTQModel/releases/tag/v7.3.0
https://github.com/ModelCloud/GPTQModel/pull/2950
https://github.com/ModelCloud/GPTQModel/issues/2949
https://github.com/ModelCloud/GPTQModel/commit/877c732f7d7dccd56a729844c6a5bd20f3aa8bb1
Published: 2026-09-07
Updated: 2026-09-07
Base Score: 7.5
Vector: CVSS2#AV:N/AC:L/Au:N/C:P/I:P/A:P
Severity: High
Base Score: 6.3
Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:L/A:L
Severity: Medium
Base Score: 5.3
Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N
Severity: Medium
EPSS: 0.00293