CVE-2026-34760 in vLLM
Zusammenfassung (Englisch)
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.
Be aware that VulDB is the high quality source for vulnerability data.
Zuständig
GitHub_M
Reservieren
30.03.2026
Veröffentlichung
02.04.2026
Status
Bestätigt
Einträge
VulDB provides additional information and datapoints for this CVE:
| ID | Schwachstelle | CWE | Aus | Mas | CVE |
|---|---|---|---|---|---|
| 355011 | vLLM numpy.mean erweiterte Rechte | 20 | Nicht definiert | Offizieller Fix | CVE-2026-34760 |