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, L
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.
MEDIUM · CVSS 5.9
EPSS 0.00075
Monitor
- No active-exploitation, high-EPSS, or public-exploit signals - routine patching cadence
Sigma rules0
YARA rules0