CVE-2026-126398

high

Description

vLLM from 0.28.0 before 0.30.0 contains a reachable assertion vulnerability in GPUModelRunner._init_xdrope_positions that allows remote attackers to crash the engine by submitting embeddings-only requests. Attackers can send a /v1/completions request containing only prompt_embeds to XD-RoPE models with --enable-prompt-embeds, terminating the EngineCore and API server for all clients.

References

https://www.vulncheck.com/advisories/vllm-0.28.0-before-0.30.0-denial-of-service-via-prompt-embeds-on-xd-rope-models

https://github.com/vllm-project/vllm/security/advisories/GHSA-5q78-j82c-2vr2

https://euvd.enisa.europa.eu/vulnerability/EUVD-2026-125167

Details

Source: Mitre, NVD

Published: 2026-11-13

Updated: 2026-11-17

Risk Information

CVSS v2

Base Score: 5.4

Vector: CVSS2#AV:N/AC:H/Au:N/C:N/I:N/A:C

Severity: Medium

CVSS v3

Base Score: 5.9

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

Severity: Medium

CVSS v4

Base Score: 8.2

Vector: 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

Severity: High

EPSS

EPSS: 0.00367