CVE-2026-126398
Published:November 13, 2026
Updated:November 21, 2026
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.
Affected Packages
vllm (CONDA):
Affected version(s) >=0.19.1 <0.30.0Fix Suggestion:
Update to version 0.30.0https://github.com/vllm-project/vllm.git (GITHUB):
Affected version(s) >=v0.12.0 <v0.30.0Fix Suggestion:
Update to version v0.30.0vllm (PYTHON):
Affected version(s) >=0.12.0 <0.30.0Fix Suggestion:
Update to version 0.30.0Related Resources (4)
Do you need more information?
Contact UsCVSS v4
Base Score:
8.2
Attack Vector
NETWORK
Attack Complexity
HIGH
Attack Requirements
PRESENT
Privileges Required
NONE
User Interaction
NONE
Vulnerable System Confidentiality
NONE
Vulnerable System Integrity
NONE
Vulnerable System Availability
HIGH
Subsequent System Confidentiality
NONE
Subsequent System Integrity
NONE
Subsequent System Availability
NONE
CVSS v3
Base Score:
5.9
Attack Vector
NETWORK
Attack Complexity
HIGH
Privileges Required
NONE
User Interaction
NONE
Scope
UNCHANGED
Confidentiality
NONE
Integrity
NONE
Availability
HIGH
Weakness Type (CWE)
Reachable Assertion
EPSS
Base Score:
0.37