CVE-2026-94626

vLLM through 0.29.0 fails to validate the tp_size parameter in kv_transfer_params on OpenAI-compatible completion endpoints, allowing attackers to allocate unbounded memory. Attackers can supply arbitrary tp_size values in prefill/decode disaggregated deployments to exhaust memory and trigger kernel OOM-kill of the decode worker process.

  • Published Sep 21, 2026
  • CVSS 8.7 high
  • 0.6% chance of exploitation in the next 30 days (EPSS)
  • A fix is available

Affected software

CVE-2026-94626 at the National Vulnerability Database