CVE-2026-34760

medium Red Hat
CVSS v3 Base Score
5.9
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:H/A:N
EPSS Score
0.1%
Exploitation probability in 30 days
Top 77% most likely to be exploited
Attack Characteristics
Attack Vector
Network
Attack Complexity
High
Privileges Required
None
User Interaction
None
Confidentiality
None
Integrity
High
Availability
None
Published: April 2, 2026 (99 days ago)
Last Modified: April 2, 2026
Vendor: Red Hat
Source: REDHAT

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.

CWE

CWE-358

Affected Products

Red Hat AI Inference ServerRed Hat Enterprise Linux AI (RHEL AI) 3Red Hat OpenShift AI (RHOAI)

References

🔗 bugzilla.redhat.com 🔗 www.cve.org 🔗 nvd.nist.gov 🔗 github.com 🔗 github.com