PatchSiren cyber security CVE debrief
CVE-2026-86288 ModelCloud CVE debrief
A vulnerability was found in ModelCloud GPTQModel up to 7.2.0, affecting the Triton dequantization kernel in the file gptqmodel/nn_modules/qlinear/tritonv2.py. This issue allows for an out-of-bounds read due to manipulation of the argument g_idx, which can be exploited remotely. The exploit has been disclosed publicly. Upgrading to version 7.3.0 resolves this issue, with the patch being 877c732f7d7dccd56a729844c6a5bd20f3aa8bb1.
- Vendor
- ModelCloud
- Product
- GPTQModel
- CVSS
- LOW 2.1
- CISA KEV
- Not listed in stored evidence
- Original CVE published
- 2026-09-07
- Original CVE updated
- 2026-09-07
- Advisory published
- 2026-09-07
- Advisory updated
- 2026-09-07
Who should care
Defenders responsible for ModelCloud GPTQModel deployments should assess the vulnerability and prioritize upgrading to version 7.3.0 if affected. This includes operators, platform administrators, vulnerability management teams, and security teams who need to verify exposure, apply the patch, and monitor for potential exploitation attempts.
Why it matters
CVE-2026-86288 is a vulnerability in ModelCloud GPTQModel that allows for remote exploitation leading to out-of-bounds read. Defenders should verify exposure, prioritize patching, and monitor for exploitation attempts.
- Verify exposure of ModelCloud GPTQModel versions up to 7.2.0 in the environment.
- Assess the need for and apply the patch 877c732f7d7dccd56a729844c6a5bd20f3aa8bb1.
- Monitor for potential exploitation attempts targeting this vulnerability.
Technical summary
The vulnerability affects ModelCloud GPTQModel up to version 7.2.0, specifically in the Triton dequantization kernel within the file gptqmodel/nn_modules/qlinear/tritonv2.py. An out-of-bounds read can occur due to manipulation of the g_idx argument. This issue can be exploited remotely. The exploit has been disclosed publicly. Upgrading to version 7.3.0 resolves this issue, with the patch being 877c732f7d7dccd56a729844c6a5bd20f3aa8bb1. Defenders should prioritize verifying exposure of ModelCloud GPTQModel versions up to 7.2.0 and assess the need for upgrading to version 7.3.0.
Defensive priority
Defenders should prioritize verifying exposure of ModelCloud GPTQModel versions up to 7.2.0 and assess the need for upgrading to version 7.3.0.
Recommended defensive actions
- Verify if ModelCloud GPTQModel versions up to 7.2.0 are in use and assess the need for upgrading to version 7.3.0.
- Apply the patch 877c732f7d7dccd56a729844c6a5bd20f3aa8bb1 to affected systems.
- Monitor for potential exploitation attempts targeting this vulnerability.
- Review compensating controls for exposed systems while remediation is scheduled and verified.
- Check relevant monitoring, detection, and logs for exposed assets that need extra review.
- Track exceptions, retest remediated assets, and close the item only after evidence is documented.
- Confirm whether affected product deployments exist in managed environments and assign an owner for follow-up.
Evidence notes
The CVE record and source references provide details on the vulnerability, its impact, and the available patch. However, the corpus does not establish versions, exploitation, impact, or remediation beyond upgrading to version 7.3.0.
Sources and references
Verified primary and authoritative sources
-
CVE-2026-86288 CVE Program record
Publisher, destination, and source semantics verified
URL: https://www.cve.org/CVERecord?id=CVE-2026-86288
CVE Program - Official CVE Program record with source-provided CVE metadata.
-
CVE-2026-86288 NVD vulnerability detail
Publisher, destination, and source semantics verified
URL: https://nvd.nist.gov/vuln/detail/CVE-2026-86288
NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.
Supplemental references
-
Source reference
Unverified legacy reference
URL: https://github.com/ModelCloud/GPTQModel/
-
Source reference
Unverified legacy reference
URL: https://github.com/ModelCloud/GPTQModel/commit/877c732f7d7dccd56a729844c6a5bd20f3aa8bb1
-
Source reference
Unverified legacy reference
URL: https://github.com/ModelCloud/GPTQModel/issues/2949
-
Source reference
Unverified legacy reference
URL: https://github.com/ModelCloud/GPTQModel/pull/2950
-
Source reference
Unverified legacy reference
URL: https://github.com/ModelCloud/GPTQModel/releases/tag/v7.3.0
-
Source reference
Unverified legacy reference
URL: https://vuldb.com/cve/CVE-2026-86288
-
Source reference
Unverified legacy reference
URL: https://vuldb.com/submit/906135
-
Source reference
Unverified legacy reference
URL: https://vuldb.com/vuln/399447
Methodology and review provenance
AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.