---
id: "CVE-2026-116502"
kind: "vulnerability"
aliases: ["CVE-2026-116502"]
title: "ExLlamaV2: crafted g_idx input causes out-of-bounds write locally"
severity: "medium"
cvss: 4.8
epss: null
exploited: false
status: "open"
category: "ai-tooling"
products: []
ecosystems: []
tags: ["ai-tooling", "cuda", "exllamav2", "gpu", "local-inference", "python"]
not_affected_if: ["models-from-trusted-sources-only", "no-exllamav2"]
published_at: "2026-10-26T21:18:12+00:00"
first_seen_at: "2026-10-26T21:20:31+00:00"
updated_at: "2026-10-26T21:21:18+00:00"
sources: [{"source": "nvd", "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-116502", "first_seen_at": "2026-10-26T21:20:31+00:00"}]
---

# ExLlamaV2: crafted g_idx input causes out-of-bounds write locally

ExLlamaV2 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, check and fix written by a model from the sources; labelled as such._

## How to check

- Check the installed version with `pip show exllamav2` and see whether it is `0.3.2` or earlier.
- Look for any loader that accepts untrusted GPTQ-quantized model files with exllamav2.

## Fix

- unknown; the sources say the project has not responded yet. Watch the upstream repository for a patched release and avoid loading untrusted quantized models in the meantime.

## Timeline

- 2026-10-26T21:20:31+00:00 nvd https://nvd.nist.gov/vuln/detail/CVE-2026-116502

## From the sources

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.

---

_Free to read at a human pace. An API with keys and an MCP server are in preparation; early access: hello@infrastack.ai_