CVE-2026-34760
vLLM is an inference and serving engine for large language models …
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.
What to do now
- Check your exposureFind out whether the affected software runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Set the orderSystems that can be reached from the internet come first, then the rest.
References
- github.com/vllm-project/vllm/commit/c7f98b4d0a63b32ed939e2b6dfaa8a626e9b46c4
- github.com/vllm-project/vllm/pull/37058
- github.com/vllm-project/vllm/releases/tag/v0.18.0
- github.com/vllm-project/vllm/security/advisories/GHSA-6c4r-fmh3-7rh8
- nvd.nist.gov/vuln/detail/CVE-2026-34760
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2299.yaml
- github.com/advisories/GHSA-6c4r-fmh3-7rh8
- nvd.nist.gov/vuln/detail/CVE-2026-34760
- cve.org/CVERecord?id=CVE-2026-34760
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.