CVSS 3.1
7.1 highCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:LCVE-2026-34760
High (7.1) in vllm vllm. EPSS 0.3% chance of exploitation in the next 30 days. Fixed in vllm 0.18.0.
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.
Severity
- EPSS
- 0.3% chance of exploitation in the next 30 days; higher than 20% of CVEs (scores of 2026-10-31)
- CWE
- CWE-20
- Published
- Modified
- Record from
- the NVD, synced
Affected
- vllm:vllm
Packages (OSV)
| Advisory | Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|---|
| GHSA-6c4r-fmh3-7rh8 | PyPI | vllm | >=0.5.5 <0.18.0 | 0.18.0 |
| PYSEC-2026-2299 | PyPI | vllm | >=0.5.5 <0.18.0 | 0.18.0 |