CVE-2026-34760
5.9
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:H/A:L
Summary
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 Software
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| vllm-project | vllm | >= 0.5.5, < 0.18.0 | affected |
Weaknesses
- CWE-20: CWE-20: Improper Input Validation
ADP Enrichment
CISA ADP Vulnrichment
- SSVC:
- Exploitation: none
- Automatable: no
- Technical Impact: partial
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-6c4r-fmh3-7rh8
- https://github.com/vllm-project/vllm/pull/37058
- https://github.com/vllm-project/vllm/commit/c7f98b4d0a63b32ed939e2b6dfaa8a626e9b46c4
- https://github.com/vllm-project/vllm/releases/tag/v0.18.0
Feedback
Was this page helpful?
Glad to hear it! Please tell us how we can improve.
Sorry to hear that. Please tell us how we can improve.