Логотип exploitDog
Консоль
Логотип exploitDog

exploitDog

debian логотип

CVE-2026-34760

Опубликовано: 02 апр. 2026
Источник: debian
EPSS Низкий

Описание

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.

Пакеты

ПакетСтатусВерсия исправленияРелизТип
vllmitppackage

EPSS

Процентиль: 19%
0.00267
Низкий

Связанные уязвимости

CVSS3: 5.9
redhat
4 месяца назад

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.

CVSS3: 5.9
nvd
4 месяца назад

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.

CVSS3: 5.9
github
25 дней назад

vLLM: Processing differential in multi-channel audio downmixing enables hidden-input/moderation bypass for audio models

EPSS

Процентиль: 19%
0.00267
Низкий