p PatchFirst

CVE-2026-34760

CVE-2026-34760 · vLLM: Downmix Implementation Differences as Attack Vectors Against Audio AI Models

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

vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before version 0.18.0, Librosa defaults to using numpy.mean for mono downmixing (to_mono), while the international standard ITU-R BS.775-4 specifies a weighted downmixing algorithm. This discrepancy results in inconsistency between audio heard by humans (e.g., through headphones/regular speakers) and audio processed by AI models (Which infra via Librosa, such as vllm, transformer). This issue has been patched in version 0.18.0.

CVSS 5.9 · Medium · EPSS 0.3% · Fix available

Published
Updated

Stack: python

Affected products and versions

  • vllm

    Versions
    • >= 0.5.5, < 0.18.0: Affected

    No fix published

  • vllm PyPI

    Versions
    • 0.10.0
    • 0.10.1
    • 0.10.1.1
    • 0.10.2
    • 0.11.0
    • 0.11.1
    • 0.11.2
    • 0.12.0
    • 0.13.0
    • 0.14.0
    • 0.14.1
    • 0.15.0
    • 0.15.1
    • 0.16.0
    • 0.17.0
    • 0.17.1
    • 0.5.5
    • 0.6.0
    • 0.6.1
    • 0.6.1.post1
    • 0.6.1.post2
    • 0.6.2
    • 0.6.3
    • 0.6.3.post1
    • 0.6.4
    • 0.6.4.post1
    • 0.6.5
    • 0.6.6
    • 0.6.6.post1
    • 0.7.0
    • 0.7.1
    • 0.7.2
    • 0.7.3
    • 0.8.0
    • 0.8.1
    • 0.8.2
    • 0.8.3
    • 0.8.4
    • 0.8.5
    • 0.8.5.post1
    • 0.9.0
    • 0.9.0.1
    • 0.9.1
    • 0.9.2
    Affected ranges
    • ECOSYSTEM: ≥ 0.5.5, < 0.18.0

    Update to 0.18.0

Original sources

Check your server →