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.
{
"cna_assigner": "VulnCheck",
"cwe_ids": [
"CWE-789"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/94xxx/CVE-2026-94626.json"
}