Sign In
Advisories

vLLM from 0.8.5 before 0.31.0 Cross-Tenant DoS via Uninitialized LogprobsTensors

Go back
Severity
high
Date
Affecting

  • vllm >= 0.8.5, < 0.31.0

CWE
  • CWE-908 Use of Uninitialized Resource
CVSS
8.3
CVSS V4 Vector
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:H
Credit
mcgrof, jperezdealgaba
Description
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.

Ready to get Started?

Explore VulnCheck, a next-generation Cyber Threat Intelligence platform, which provides exploit and vulnerability intelligence to help you prioritize and remediate vulnerabilities that matter.
  • Vulnerability Prioritization
    Prioritize vulnerabilities that matter based on the threat landscape and defer vulnerabilities that don't.
  • Early Warning System
    Real-time alerting of changes in the vulnerability landscape so that you can take action before the attacks start.
Schedule a Demo