CVE-2026-116178 | BDVDB-2026-395366 Detail

Description#

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.

Impact#

Weaknesses#

References#

Exploit#

History#

1. Version 12026-10-25Record published in the CVE List.
2. Version 22026-10-26Most recent update recorded in the CVE List.