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.
Ссылки
- Patch
- Issue Tracking
- Release Notes
- Vendor Advisory
Уязвимые конфигурации
EPSS
5.9 Medium
CVSS3
7.1 High
CVSS3
Дефекты
Связанные уязвимости
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.
vLLM is an inference and serving engine for large language models (LLM ...
vLLM: Processing differential in multi-channel audio downmixing enables hidden-input/moderation bypass for audio models
EPSS
5.9 Medium
CVSS3
7.1 High
CVSS3