CVE-2026-116180
Published:October 25, 2026
Updated:October 29, 2026
vLLM from 0.8.5 before 0.31.0 has a denial of service flaw. LogprobsTensors.empty_cpu() in vllm/v1/outputs.py allocates an uninitialized int32 tensor, and the V1 model runner leaves prompt positions reported as computed by a KV connector unwritten. A client sharing the engine can send prompt_logprobs (or echo with logprobs) against a connector-cached prefix, making tokenizer decode raise OverflowError, which crashes EngineCore and drops all co-tenant requests.
Affected Packages
vllm (CONDA):
Affected version(s) >=0.9.2 <0.31.0Fix Suggestion:
Update to version 0.31.0https://github.com/vllm-project/vllm.git (GITHUB):
Affected version(s) >=v0.8.5 <v0.31.0Fix Suggestion:
Update to version v0.31.0vllm (PYTHON):
Affected version(s) >=0.8.5 <0.31.0Fix Suggestion:
Update to version 0.31.0Related Resources (2)
Do you need more information?
Contact UsCVSS v4
Base Score:
8.3
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
HIGH
CVSS v3
Base Score:
7.7
Attack Vector
NETWORK
Attack Complexity
LOW
Privileges Required
LOW
User Interaction
NONE
Scope
CHANGED
Confidentiality
NONE
Integrity
NONE
Availability
HIGH
Weakness Type (CWE)
Use of Uninitialized Resource
EPSS
Base Score:
0.25