{"id":27365,"date":"2026-09-22T08:31:03","date_gmt":"2026-09-22T00:31:03","guid":{"rendered":"https:\/\/www.54iter.cn\/?vuln=cve-2026-94626"},"modified":"2026-09-22T08:31:03","modified_gmt":"2026-09-22T00:31:03","slug":"cve-2026-94626","status":"publish","type":"vuln","link":"https:\/\/www.54iter.cn\/?vuln=cve-2026-94626","title":{"rendered":"CVE-2026-94626 [HIGH] &#8211; vLLM through 0.29.0 fails to validate the tp_size parameter in kv_transfer_params on OpenA"},"content":{"rendered":"<p>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.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>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 arbit<\/p>\n","protected":false},"template":"","meta":[],"categories":[],"tags":[],"class_list":["post-27365","vuln","type-vuln","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/www.54iter.cn\/index.php?rest_route=\/wp\/v2\/vuln\/27365","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.54iter.cn\/index.php?rest_route=\/wp\/v2\/vuln"}],"about":[{"href":"https:\/\/www.54iter.cn\/index.php?rest_route=\/wp\/v2\/types\/vuln"}],"wp:attachment":[{"href":"https:\/\/www.54iter.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=27365"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.54iter.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=27365"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.54iter.cn\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=27365"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}