← Retour aux CVEs

CVE-2026-34760

MEDIUM

5.9

Description

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.

Details CVE

Score CVSS v3.15.9

SeveriteMEDIUM

Vecteur CVSSCVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:H/A:L

Vecteur d'attaqueNETWORK

ComplexiteHIGH

Privileges requisLOW

Interaction utilisateurNONE

Publie4/2/2026

Derniere modification4/3/2026

Sourcenvd

Observations honeypot0

Faiblesses (CWE)

CWE-20

References

https://github.com/vllm-project/vllm/commit/c7f98b4d0a63b32ed939e2b6dfaa8a626e9b46c4(security-advisories@github.com)

https://github.com/vllm-project/vllm/pull/37058(security-advisories@github.com)

https://github.com/vllm-project/vllm/releases/tag/v0.18.0(security-advisories@github.com)

https://github.com/vllm-project/vllm/security/advisories/GHSA-6c4r-fmh3-7rh8(security-advisories@github.com)

Correlations IOC

Aucune correlation enregistree

This product uses data from the NVD API but is not endorsed or certified by the NVD.