CVE-2026-34760
Last modified
CVE-2026-34760 is a high-severity vulnerability rated 7.1/10 on the CVSS scale. 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. EPSS estimates a 0.27% chance of exploitation in the next 30 days.
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.
Metrics
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:L
Weakness Enumeration
Affected Software
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | >= 0.5.5, < 0.18.0 |
References
- https://github.com/vllm-project/vllm/pull/37058Issue Tracking
Timeline
- Published
- Last Modified
- Status
- Analyzed
Frequently Asked Questions
What is CVE-2026-34760?
How severe is CVE-2026-34760?
How do I fix CVE-2026-34760?
Are you affected by CVE-2026-34760?
Run a free Strix scan to check your systems for this vulnerability.
Scan your code nowSource: NVD / NIST
