{"id":26720,"date":"2026-09-19T04:31:43","date_gmt":"2026-09-18T20:31:43","guid":{"rendered":"https:\/\/www.54iter.cn\/?vuln=cve-2026-93840"},"modified":"2026-09-19T04:31:43","modified_gmt":"2026-09-18T20:31:43","slug":"cve-2026-93840","status":"publish","type":"vuln","link":"https:\/\/www.54iter.cn\/?vuln=cve-2026-93840","title":{"rendered":"CVE-2026-93840 [LOW] &#8211; vLLM before 0.29.0 validates allowed_token_ids against tokenizer length instead of model o"},"content":{"rendered":"<p>vLLM before 0.29.0 validates allowed_token_ids against tokenizer length instead of model output logits width in SamplingParams._validate_allowed_token_ids(). Attackers can supply token IDs above the output vocabulary that pass validation, causing LogitBiasState to corrupt GPU logits state and allow concurrent requests to sample tokens outside their allowlists.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>vLLM before 0.29.0 validates allowed_token_ids against tokenizer length instead of model output logits width in SamplingParams._validate_allowed_token_ids(). Attackers can supply token IDs above the o<\/p>\n","protected":false},"template":"","meta":[],"categories":[],"tags":[],"class_list":["post-26720","vuln","type-vuln","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/www.54iter.cn\/index.php?rest_route=\/wp\/v2\/vuln\/26720","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=26720"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.54iter.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=26720"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.54iter.cn\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=26720"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}