CVE-2026-34760: 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…

PriorityP337high7.1CVSS 3.1

AVNACLPRLUINSUCNIHAL

EPSS

0.27%

18.2th percentile

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.

Affected

2 ranges

Vendor	Product	Version range	Fixed in
vllm-project	vllm	—	—
vllm	vllm	>= 0.5.5 < 0.18.0	0.18.0

CVSS provenance

nvdv3.17.1HIGHCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:L

vendor_redhat5.9MEDIUM

Stop checking back — get the weekly exploitation signal.

Every Monday: what got weaponized or added to CISA KEV in the last seven days — each CVE cross-linked to its PoC, Nuclei template, and detection rule. Free, one email a week, unsubscribe in one click.