CVE-2026-34760
vllm-project vllm 취약점
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.
- 대응 우선순위
- 점검
- CVSS
- 7.1
- EPSS
- 0.27% 백분위 18.7% · 2026.08.04 기준
- CISA KEV
- 미등록
- 조치 기한
- -
- 공개일
- 2026.04.03