CVE-2026-126399
Published:November 13, 2026
Updated:November 21, 2026
vLLM from 0.19.0 before 0.31.0 contains a resource exhaustion vulnerability that allows inference clients to bypass the server frame limit by setting media_io_kwargs.video.num_frames in chat completion requests. Attackers can supply num_frames=-1 or a large value with many base64 JPEG frames, forcing VideoMediaIO to decode all frames and np.stack them, causing memory exhaustion.
Affected Packages
vllm (CONDA):
Affected version(s) >=0.19.1 <0.31.0Fix Suggestion:
Update to version 0.31.0https://github.com/vllm-project/vllm.git (GITHUB):
Affected version(s) >=v0.19.0rc1 <v0.31.0Fix Suggestion:
Update to version v0.31.0vllm (PYTHON):
Affected version(s) >=0.19.0 <0.31.0Fix Suggestion:
Update to version 0.31.0Related ResourcesĀ (4)
Do you need more information?
Contact UsCVSS v4
Base Score:
7.1
Attack Vector
NETWORK
Attack Complexity
LOW
Attack Requirements
NONE
Privileges Required
LOW
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:
6.5
Attack Vector
NETWORK
Attack Complexity
LOW
Privileges Required
LOW
User Interaction
NONE
Scope
UNCHANGED
Confidentiality
NONE
Integrity
NONE
Availability
HIGH
Weakness Type (CWE)
Allocation of Resources Without Limits or Throttling
EPSS
Base Score:
0.41