{"id":4002,"date":"2023-10-30T05:55:00","date_gmt":"2023-10-29T20:55:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=4002"},"modified":"2023-10-30T05:55:00","modified_gmt":"2023-10-29T20:55:00","slug":"deja-vu-contextual-sparsity-for-efficient-llms-at-inference-time","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=4002","title":{"rendered":"Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time\u00a0<\/strong>[91.0]<br>\u6570\u5341\u5104\u306e\u30d1\u30e9\u30e1\u30fc\u30bf\u3092\u6301\u3064\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb(LLM)\u304c\u3001\u30a8\u30ad\u30b5\u30a4\u30c6\u30a3\u30f3\u30b0\u306aAI\u30a2\u30d7\u30ea\u30b1\u30fc\u30b7\u30e7\u30f3\u306b\u65b0\u305f\u306a\u6ce2\u3092\u5dfb\u304d\u8d77\u3053\u3057\u305f\u3002 \u65e2\u5b58\u306e\u65b9\u6cd5\u306f\u3001\u30b3\u30b9\u30c8\u306e\u304b\u304b\u308b\u518d\u8a13\u7df4\u304c\u5fc5\u8981\u304b\u3001LLM\u306e\u30b3\u30f3\u30c6\u30ad\u30b9\u30c8\u5185\u5b66\u7fd2\u80fd\u529b\u3092\u6368\u3066\u308b\u304b\u3001\u30a6\u30a9\u30fc\u30eb\u30af\u30ed\u30c3\u30af\u306e\u30b9\u30d4\u30fc\u30c9\u30a2\u30c3\u30d7\u3092\u9054\u6210\u3067\u304d\u306a\u3044\u304b\u306e\u3044\u305a\u308c\u304b\u3067\u3042\u308b\u3002 DejaVu\u306f,\u5404\u5c64\u306b\u4e0e\u3048\u3089\u308c\u305f\u5165\u529b\u3092\u30ea\u30a2\u30eb\u30bf\u30a4\u30e0\u3067\u4e88\u6e2c\u3059\u308b\u305f\u3081\u306b,\u4f4e\u30b3\u30b9\u30c8\u306a\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u7528\u3044\u305f\u30b7\u30b9\u30c6\u30e0\u3067\u3042\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2310.17157v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2310.17157v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 26 Oct 2023 05:01:09 GMT)<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/FMInference\/DejaVu\">GitHub &#8211; FMInference\/DejaVu<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[223,551],"class_list":["post-4002","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-llm","tag-551"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4002","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=4002"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4002\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4002"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4002"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4002"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}