CVE-2026-100649
Published:September 26, 2026
Updated:October 10, 2026
vLLM before 0.29.0 contains a resource-limit bypass vulnerability in PyNvVideoCodec decoder allocation where sampler subclass shadowing allows independent counter increments. Unauthenticated attackers can select different sampler subclasses in video requests to exceed configured decoder limits and exhaust unaccounted GPU memory.
Affected Packages
vllm (CONDA):
Affected version(s) >=0.25.0 <0.29.0Fix Suggestion:
Update to version 0.29.0https://github.com/vllm-project/vllm.git (GITHUB):
Affected version(s) >=v0.25.0rc1 <v0.29.0Fix Suggestion:
Update to version v0.29.0vllm (PYTHON):
Affected version(s) >=0.25.0 <0.29.0Fix Suggestion:
Update to version 0.29.0Related Resources (4)
Do you need more information?
Contact UsCVSS v4
Base Score:
6.3
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
LOW
Subsequent System Confidentiality
NONE
Subsequent System Integrity
NONE
Subsequent System Availability
NONE
CVSS v3
Base Score:
3.7
Attack Vector
NETWORK
Attack Complexity
HIGH
Privileges Required
NONE
User Interaction
NONE
Scope
UNCHANGED
Confidentiality
NONE
Integrity
NONE
Availability
LOW
Weakness Type (CWE)
Allocation of Resources Without Limits or Throttling
EPSS
Base Score:
0.34