Signal is active with 1 mentions in latest observed window
Recommended action window: Monitor and triage in normal cycle
NVD description
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.
Priority
LOW
Exploitation
NONE
PoC
NONE
Patch
AVAILABLE
Momentum
NONE
If you run products in this scope, you should treat this CVE as relevant to your environment.
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, Librosa defaults to using numpy.mean for mono d… https://www.cve.org/CVERecord?id=CVE-2026-34760
Post summary
The snippet identifies CVE-2026-34760 and notes a Librosa default behavior, but it does not provide evidence of exploitation, patches, or a PoC.
1 of 1 entries
| Part | Vendor | Product | Version | Target SW | Target HW |
|---|---|---|---|---|---|
| App | vllm | vllm | - | - | - |