{"id":5723,"date":"2024-11-07T05:54:00","date_gmt":"2024-11-06T20:54:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5723"},"modified":"2024-11-07T05:54:00","modified_gmt":"2024-11-06T20:54:00","slug":"neuzip-memory-efficient-training-and-inference-with-dynamic-compression-of-neural-networks","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5723","title":{"rendered":"NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks\u00a0<\/strong>[30.2]<br>NeuZip\u306f\u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u306b\u304a\u3051\u308b\u6d6e\u52d5\u5c0f\u6570\u70b9\u6570\u306e\u30a8\u30f3\u30c8\u30ed\u30d4\u30fc\u306b\u57fa\u3065\u304f\u65b0\u3057\u3044\u91cd\u307f\u5727\u7e2e\u65b9\u5f0f\u3067\u3042\u308b\u3002 Llama-3 8B\u30e2\u30c7\u30eb\u306e\u30e1\u30e2\u30ea\u30d5\u30c3\u30c8\u30d7\u30ea\u30f3\u30c8\u309231GB\u304b\u308916GB\u4ee5\u4e0b\u306b\u5927\u5e45\u306b\u524a\u6e1b\u3057\u305f\u3002 \u63a8\u5b9a\u3067\u306f, \u307b\u307c\u30ed\u30b9\u30ec\u30b9\u6027\u80fd\u3092\u7dad\u6301\u3057\u306a\u304c\u3089, \u30e1\u30e2\u30ea\u4f7f\u7528\u91cf\u3092\u534a\u6e1b\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2410.20650v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2410.20650v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Mon, 28 Oct 2024 01:12:20 GMT)<\/li>\n\n\n\n<li>\u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u306e\u5727\u7e2e\uff08\u30e1\u30e2\u30ea\u524a\u6e1b\uff09\u624b\u6cd5\u306e\u63d0\u6848\u3002\u91cf\u5b50\u5316\u306a\u3069\u3068\u7570\u306a\u308a\u30ed\u30b9\u30ec\u30b9\u3067\u5b9f\u7528\u7684\u3068\u601d\u308f\u308c\u308b\u624b\u6cd5\u3067\u3042\u308b\u306e\u304c\u8208\u5473\u6df1\u3044\u3002\u4e0d\u53ef\u9006\u306a\u624b\u6cd5\u3067\u3082\u300cThe lossy NeuZip provides additional memory saving for inference, achieving superior memory\u2013performance trade-off.\u300d\u3068\u306e\u3053\u3068\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/BorealisAI\/neuzip\">GitHub &#8211; BorealisAI\/neuzip: Official repository for the paper &#8220;NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks&#8221;. This repository contains the code for the experiments in the paper.<\/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":[223,565],"class_list":["post-5723","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-llm","tag-565"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5723","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=5723"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5723\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5723"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5723"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5723"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}