CVE-2026-105760
Published:October 05, 2026
Updated:October 11, 2026
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, a caller can use the request-level media_io_kwargs field to select the GLMGA video backend and supply large values for the fps and max_frames options without a strict work ceiling. GLMGA constructs and deduplicates an attacker-sized pre-decode frame-index list, allowing a compact request and tiny valid video to consume disproportionate CPU time and memory in the shared media-loading executor. This issue is fixed in version 0.30.0.
Affected Packages
vllm (CONDA):
Affected version(s) >=0.23.0 <0.30.0Fix Suggestion:
Update to version 0.30.0https://github.com/vllm-project/vllm.git (GITHUB):
Affected version(s) >=v0.23.0rc2 <v0.30.0Fix Suggestion:
Update to version v0.30.0vllm (PYTHON):
Affected version(s) >=0.23.0 <0.30.0Fix Suggestion:
Update to version 0.30.0Related Resources (7)
Do you need more information?
Contact UsCVSS v4
Base Score:
6.9
Attack Vector
NETWORK
Attack Complexity
LOW
Attack Requirements
NONE
Privileges Required
NONE
User Interaction
NONE
Vulnerable System Confidentiality
NONE
Vulnerable System Integrity
NONE
Vulnerable System Availability
LOW
Subsequent System Confidentiality
NONE
Subsequent System Integrity
NONE
Subsequent System Availability
NONE
CVSS v3
Base Score:
5.3
Attack Vector
NETWORK
Attack Complexity
LOW
Privileges Required
NONE
User Interaction
NONE
Scope
UNCHANGED
Confidentiality
NONE
Integrity
NONE
Availability
LOW
Weakness Type (CWE)
Uncontrolled Resource Consumption
EPSS
Base Score:
0.30