{"id":"PYSEC-2026-2299","details":"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.","aliases":["CVE-2026-34760","GHSA-6c4r-fmh3-7rh8"],"modified":"2026-07-13T07:15:12.553209687Z","published":"2026-04-02T20:16:25.437Z","references":[{"type":"ADVISORY","url":"https://github.com/vllm-project/vllm/releases/tag/v0.18.0"},{"type":"ADVISORY","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-6c4r-fmh3-7rh8"},{"type":"REPORT","url":"https://github.com/vllm-project/vllm/pull/37058"},{"type":"FIX","url":"https://github.com/vllm-project/vllm/commit/c7f98b4d0a63b32ed939e2b6dfaa8a626e9b46c4"}],"affected":[{"package":{"name":"vllm","ecosystem":"PyPI","purl":"pkg:pypi/vllm"},"ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0.5.5"},{"fixed":"0.18.0"}]}],"versions":["0.10.0","0.10.1","0.10.1.1","0.10.2","0.11.0","0.11.1","0.11.2","0.12.0","0.13.0","0.14.0","0.14.1","0.15.0","0.15.1","0.16.0","0.17.0","0.17.1","0.5.5","0.6.0","0.6.1","0.6.1.post1","0.6.1.post2","0.6.2","0.6.3","0.6.3.post1","0.6.4","0.6.4.post1","0.6.5","0.6.6","0.6.6.post1","0.7.0","0.7.1","0.7.2","0.7.3","0.8.0","0.8.1","0.8.2","0.8.3","0.8.4","0.8.5","0.8.5.post1","0.9.0","0.9.0.1","0.9.1","0.9.2"],"ecosystem_specific":{},"database_specific":{"source":"https://github.com/pypa/advisory-database/blob/main/vulns/vllm/PYSEC-2026-2299.yaml"}}],"schema_version":"1.7.5","severity":[{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:L"}]}