CVE-2026-110695
mediumpriority · track · 25EPSS 0.004 · 30 %ileEPSS · scored 2026-10-27
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.
cvss
Technical severity, 0–10. One row per scoring source.
base score 0–10 · higher = more severe · hover a vector to decode⚠ sources disagree · low–high · 1.3–7.5
ssvc
A stakeholder decision — act, attend, or track — from exploitation and impact.
weaknesses
The CWE weakness classes this flaw belongs to.
affected products
Products and version ranges known to be affected.
No affected products recorded.
sources
Which sources assert this record, and when.
references (6) nvd
External citations — patches, advisories, analysis.
- https://github.com/3em0/cve_repo/blob/main/2026/ExLlamaV2-0.3.2-Heap-Buffer-Overflow-in-the-safetensors-tensor-loader(STFile.get_tensor-stloader_read).md
- https://github.com/turboderp-org/exllamav2/issues/820
- https://vuldb.com/cve/CVE-2026-110695
- https://vuldb.com/submit/1003958
- https://vuldb.com/vuln/419848
- https://vuldb.com/vuln/419848/cti
Attackers weaponise vulnerabilities like this against internet-exposed services. See what is exposed on your perimeter with a free passive scan.
Free scan