Advisory

PYSEC-2026-2299

Also known as: CVE-2026-34760, GHSA-6c4r-fmh3-7rh8

Summary

The record has no summary.

Details

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.

Severity

High Basis: CVSS v3 score 7.1, vector CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:L

Dates

Published
2026-04-02 20:16 UTC
Modified
2026-07-13 07:15 UTC

Affected packages and fixes

vllm

PyPI · All systems

Affected

  • introduced 0.5.5, fixed 0.18.0 (ecosystem)

Fixed versions

0.18.0

Fix

  • Fixed version 0.18.0
    pip install --upgrade vllm==0.18.0

Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.

Check your own computer: guard packages check

View this record on OSV.dev

Source

Source: PyPA Advisory Database · CC BY 4.0

Sources & licences