CVE-2026-116178
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.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.32%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
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.
- CVSS 4.0
- 8.2 HIGHCVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/M
- EPSS
- 0.32% probability · 25th percentile
- Public exploits
- None in Exploit-DB
- CISA KEV
- Not listed
- Weakness
- CWE-20
- Source
- disclosure@vulncheck.com
EPSS moved from 0.3% on 26 October 2026 to 0.3% on 27 October 2026.
References
Source: NVD record, EPSS from FIRST.org, KEV from CISA, exploits from Exploit-DB. Refreshed daily. Download this record as JSON.