CVEvulnerability
CVE-2026-34760
7.1 HIGH
Official page ↗
- Status
- Analyzed
- Published
- 2026-04-02
- Last modified
- 2026-07-24
- Assigner
- [email protected]
- CVSS 3.1 ([email protected])
- 5.9 MEDIUM — CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:H/A:L
- CVSS 3.1 ([email protected])
- 7.1 HIGH — CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:L
- Weaknesses
- CWE-20
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.
Affected configurations
• vllm vllm (>= 0.5.5 < 0.18.0)
Related
Weakness · CWE (1)
- CWE-20 Improper Input Validation weakness
References
- https://github.com/vllm-project/vllm/commit/c7f98b4d0a63b32ed939e2b6dfaa8a626e9b46c4 Patch
- https://github.com/vllm-project/vllm/pull/37058 Issue Tracking
- https://github.com/vllm-project/vllm/releases/tag/v0.18.0 Release Notes
- https://github.com/vllm-project/vllm/security/advisories/GHSA-6c4r-fmh3-7rh8 Vendor Advisory