CVE-2026-110695: turboderp ExLlamaV2 Safetensors Tensor Loader stloader.py STFile.get_tensor buffer overflow

Published Oct 14, 2026
·
Updated

A vulnerability was detected in turboderp ExLlamaV2 up to 0.3.2. Affected is the function STFile.gettensor of the file exllamav2/stloader.py of the component Safetensors Tensor Loader. Performing a manipulation of the argument dataoffsets results in buffer overflow. The attack is possible to be carried out remotely. The exploit is now public and may be used. The project was informed of the problem early through an issue report but has not responded yet.

Affected Software

1 affected component
turboderp ExLlamaV2<=0.3.2

Event History

Oct 14, 2026
CVE Published
via MITRE·09:15 PM
Data Sourced
via MITRE·09:15 PM
DescriptionSeverityWeakness

Frequently Asked Questions

1

Which deployments are affected?

turboderp ExLlamaV2 versions up to and including 0.3.2 are affected in the Safetensors Tensor Loader component, specifically STFile.get_tensor in exllamav2/stloader.py.

2

What does an attacker need to do to exploit this issue?

An attacker needs to manipulate the data_offsets argument processed by STFile.get_tensor. The issue can be exploited remotely and requires user interaction, according to the supplied vector.

3

Is public exploit code available?

Yes. The exploit is public and may be used.

4

Is there a vendor response or patch available?

The project was notified early through an issue report but had not responded at the time of the report. No fixed version or mitigation is provided in the available data.

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