CVE-2026-110695 turboderp ExLlamaV2 Safetensors Tensor Loader stloader.py STFile.get_tensor buffer overflow
Remote attackers can trigger a buffer overflow in ExLlamaV2's Safetensors loader via manipulated data offsets, potentially leading to code execution or crashes.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- A user has to click or open something
- Fix
- None listed
What is CVE-2026-110695?
CVE-2026-110695 is a medium-severity memory corruption vulnerability in turboderp ExLlamaV2, published on 14 Oct 2026. An attacker can exploit it over the internet without logging in, and only if a user opens a file or follows a link.
Official description
A vulnerability was detected in turboderp ExLlamaV2 up to 0.3.2. Affected is the function STFile.get_tensor of the file exllamav2/stloader.py of the component Safetensors Tensor Loader. Performing a manipulation of the argument data_offsets 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.
Which versions are affected by CVE-2026-110695?
How do I fix CVE-2026-110695?
No fix has been published for CVE-2026-110695 yet. Limit exposure of the affected software until one is available.
Upgrade to the fixed version. Memory-safe languages, compiler hardening and fuzzing prevent most new cases. More about Memory corruption.
Is CVE-2026-110695 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-110695 exists.
Sources
Also known as GHSA-w755-fw26-6333.