p PatchFirst

CVE-2026-33625

CVE-2026-33625 · LMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loading

This page contains facts from public vulnerability sources. Check the original advisory before updating.

LMDeploy is a toolkit for compressing, deploying, and serving large language models. Versions 012.1 through 0.12.2 contain a code injection vulnerability in `lmdeploy/pytorch/config.py` line 620 that allows an attacker to execute arbitrary Python code by publishing a malicious HuggingFace model with a crafted `quantization_config.quant_dtype` value. When a user loads the model with lmdeploy, the `quant_dtype` is passed to `eval(f'torch.{quant_dtype}')` without any validation. Version 0.12.3 contains a patch.

CVSS 8.8 · High · EPSS 0.4% · Fix available

Published
Updated

Stack: python

Affected products and versions

  • lmdeploy

    Versions
    • >= 0.12.1, < 0.12.3: Affected

    No fix published

  • lmdeploy PyPI

    Versions
    • 0.12.1
    • 0.12.2
    Affected ranges
    • ECOSYSTEM: ≥ 0.12.1, < 0.12.3

    Update to 0.12.3

Original sources

Check your server →