vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the \/score and \/rerank endpoints derives each worker’s query_key value from the caller-controlled X-Request-Id header. A concurrent request that reuses a victim’s identifier can overwrite the cached query embedding so the victim’s documents are scored against the attacker’s query, and shared use counters can also cause a late-interaction cache-miss error. This issue is fixed in version 0.30.0.<\/p>\n","protected":false},"excerpt":{"rendered":"
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the \/score and \/rerank endpoints derives each worker’s query_key value from the ca<\/p>\n","protected":false},"template":"","meta":[],"categories":[],"tags":[],"class_list":["post-33015","vuln","type-vuln","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/www.54iter.cn\/index.php?rest_route=\/wp\/v2\/vuln\/33015","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=33015"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.54iter.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=33015"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.54iter.cn\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=33015"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}