HIGH7.1

PYSEC-2026-2299

Quick fix

PYSEC-2026-2299 — vllm: upgrade to the fixed version with the command below.

pip install --upgrade 'vllm>=0.18.0'

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.

Are you affected?

Enter the version of the package you're using.

Affected packages

PyPI/vllm

Introduced in: 0.5.5Fixed in: 0.18.0

Fixpip install --upgrade 'vllm>=0.18.0'

References

https://github.com/vllm-project/vllm/releases/tag/v0.18.0[ADVISORY]
https://github.com/vllm-project/vllm/security/advisories/GHSA-6c4r-fmh3-7rh8[ADVISORY]
https://github.com/vllm-project/vllm/pull/37058[REPORT]
https://github.com/vllm-project/vllm/commit/c7f98b4d0a63b32ed939e2b6dfaa8a626e9b46c4[FIX]