vLLM 0.20.0 before 0.30.0 DoS via /inference/v1/generate mm_placeholders

vLLM from 0.20.0 before 0.30.0 contains a denial of service vulnerability that allows remote attackers to crash the engine by sending inconsistent multimodal metadata to the disaggregated /inference/v1/generate endpoint. Attackers can replay a valid multimodal item with repeated or overlapping mm_placeholders ranges or mismatched kwargs_data and mm_hashes lists, producing a negative text span in Qwen2.5-VL position construction that terminates the engine.

Source published

25 Oct 2026 13:20:17 UTC

Source modified

25 Oct 2026 13:20:17 UTC

Observed here

25 Oct 2026 15:17:04 UTC

Source terms

CVE Program Terms of Use

Original source record · Cite this exact observation · Complete original publisher JSON

This view projects the publisher's source fields for reading; the original JSON retains additional fields and CVE enrichment containers. Attribution: cve-program · CVE Program Terms of Use. Source text is retained; field grouping and change labels are provided by ChangeIntel.

CVSS 4.0 · 8.2 CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N

CVSS 3.1 · 5.9 CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H