CVE-2026-34760
MEDIUM SEVERITYCVSS Score & Metrics
Base Score
5.9 / 10
Vector String
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:H/A:L
Vulnerability 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.
Vulnerability Details
Published Date
Last Modified
CWE ID
CWE-20
Source
NVD
Vendor
vllm-project
Product
vllm
Discussion (0)
Add Comment
No comments yet. Be the first!