Live › vulnerability › CVE-2026-116502
Go to dashboardExLlamaV2 up to 0.3.2 has an out-of-bounds write in the GPTQ index handling code (QMatrix::make_sequential in the CUDA extension) when the g_idx argument is manipulated. A local attacker who can supply a crafted quantized model could corrupt memory, with possible code execution unknown from the sources.
Summary written from the sources below. Check the originals before acting.
First seen by InfraStack 2026-10-26 21:20 UTC. All times on this page are UTC.
Teams that run ExLlamaV2 for local GPU inference on quantized (GPTQ-format) models, especially if they load model files from outside sources. The attack needs local access, so a service that only loads models you built yourself is lower risk. Teams not using ExLlamaV2 can skip it.
No product ranges from the sources yet.
pip show exllamav2 and see whether it is 0.3.2 or earlier.Each row is the first time that source carried this signal. The analyst’s rows are its own findings.
A flaw has been found in turboderp-org ExLlamaV2 up to 0.3.2. The impacted element is the function QMatrix::make_sequential of the file exllamav2/exllamav2_ext/cuda/q_matrix.cu of the component GPTQ Index Handler. Executing a manipulation of the argument g_idx can lead to out-of-bounds write. The attack needs to be launched locally. The project was informed of the problem early through an issue report but has not responded yet.
This page as .md · .json · in your agent: get_signal("CVE-2026-116502")
NVD data is provided by NIST and is public domain. Posts quoted belong to their authors.