{"cve":"CVE-2025-62372","nvd":{"published":"2025-11-21T02:15:43.393","modified":"2026-10-19T13:10:00.110","status":"Analyzed","description":"vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, users can crash the vLLM engine serving multimodal models by passing multimodal embedding inputs with correct ndim but incorrect shape (e.g. hidden dimension is wrong), regardless of whether the model is intended to support such inputs (as defined in the Supported Models page). This issue has been patched in version 0.11.1.","cvss_v4":{"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:H","score":8.3},"cvss_v3":{"version":"3.1","vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","score":6.5},"cwes":["CWE-129"],"references":["https://github.com/vllm-project/vllm/commit/58fab50d82838d5014f4a14d991fdb9352c9c84b","https://github.com/vllm-project/vllm/pull/27204","https://github.com/vllm-project/vllm/pull/6613","https://github.com/vllm-project/vllm/security/advisories/GHSA-pmqf-x6x8-p7qw"],"products":["vllm:vllm"],"source":"nvd","synced_at":"2026-10-19T22:16:02.354564667+00:00"},"epss":{"cve":"CVE-2025-62372","score":0.0041,"percentile":0.34936,"date":"2026-10-25"},"kev":null,"osv":[{"id":"GHSA-pmqf-x6x8-p7qw","url":"https://osv.dev/vulnerability/GHSA-pmqf-x6x8-p7qw","summary":"vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs","modified":"2026-09-10T03:50:58.359703609Z","packages":[{"ecosystem":"PyPI","name":"vllm","purl":"pkg:pypi/vllm","ranges":[">=0.5.5 <0.11.1"],"fixed":["0.11.1"]}]},{"id":"PYSEC-2026-2019","url":"https://osv.dev/vulnerability/PYSEC-2026-2019","summary":"vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs","modified":"2026-07-07T17:48:16.124043432Z","packages":[{"ecosystem":"PyPI","name":"vllm","purl":"pkg:pypi/vllm","ranges":[">=0.5.5 <0.11.1"],"fixed":["0.11.1"]}]}],"attribution":["This product uses the NVD API but is not endorsed or certified by the NVD.","EPSS scores: FIRST Exploit Prediction Scoring System, https://www.first.org/epss","Known exploited vulnerabilities: CISA Known Exploited Vulnerabilities Catalog, https://www.cisa.gov/known-exploited-vulnerabilities-catalog","Package advisories: OSV (https://osv.dev), from the GitHub Advisory Database, PyPA, Go, RustSec and other ecosystem databases, under CC-BY 4.0 or CC0","CVE records: the CVE Program's CVE List (https://www.cve.org), under its terms of use (https://www.cve.org/Legal/TermsOfUse). CVE is a registered trademark of The MITRE Corporation; this product is not affiliated with the CVE Program."]}