CVE-2026-126398

vLLM 0.28.0 before 0.30.0 Denial of Service via Prompt Embeds on XD-RoPE Models

  • High 8.2

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.

Key facts

Published
13 Nov 2026
Last changed
13 Nov 2026
Assigned by
VulnCheck
EPSS
0.367% likely to be exploited in the next 30 days, higher than 31.034% of CVEs (scores for 15 Nov 2026)

Severity scores

Each score is shown as its source gave it. They are not averaged or merged.

  • 8.2CVSS 4.0, Highfrom the CNA (VulnCheck)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
  • 5.9CVSS 3.1, Mediumfrom the CNA (VulnCheck)CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H

Historical context and remediation

This reference retains the original CVE publication date. A recent record update does not mean a new attack occurred.

No separately sourced impact summary is available on this page yet. Consult the description, version data and dated exploitation evidence.

No explicit remediation statement is available on this page yet. Consult the original record and vendor references before choosing a fix.

Version statuses below come from the CNA. An “unaffected” version is not necessarily a currently supported release or proof of a patch date. EPSS is a dated risk estimate, not a count of historical attacks.

Read the original CVE record.

Affected products

VendorProductVersions
vllm-projectvllm
  • Default status: unaffected
  • 0.28.0 up to but excluding 0.30.0 (affected)
  • 0.30.0 (unaffected)

Timeline

  1. 13 Nov 2026 Published

Weakness

References