{"id":2984,"date":"2025-08-19T20:13:43","date_gmt":"2025-08-19T20:13:43","guid":{"rendered":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/?p=2984"},"modified":"2025-08-19T20:13:44","modified_gmt":"2025-08-19T20:13:44","slug":"gpu-sharing-for-cost-efficient-multi-llm-serving","status":"publish","type":"post","link":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/?p=2984","title":{"rendered":"GPU Sharing for Cost-Efficient Multi-LLM Serving"},"content":{"rendered":"<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-large\"><img data-opt-id=440140424  fetchpriority=\"high\" decoding=\"async\" width=\"1024\" height=\"1024\" src=\"https:\/\/ml6vmqguit1n.i.optimole.com\/w:1024\/h:1024\/q:mauto\/f:best\/http:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/08\/Gemini_Generated_Image_m4m99rm4m99rm4m9.png\" alt=\"\" class=\"wp-image-2986\" srcset=\"https:\/\/ml6vmqguit1n.i.optimole.com\/w:1024\/h:1024\/q:mauto\/f:best\/https:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/08\/Gemini_Generated_Image_m4m99rm4m99rm4m9.png 1024w, https:\/\/ml6vmqguit1n.i.optimole.com\/w:300\/h:300\/q:mauto\/f:best\/https:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/08\/Gemini_Generated_Image_m4m99rm4m99rm4m9.png 300w, https:\/\/ml6vmqguit1n.i.optimole.com\/w:150\/h:150\/q:mauto\/f:best\/https:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/08\/Gemini_Generated_Image_m4m99rm4m99rm4m9.png 150w, https:\/\/ml6vmqguit1n.i.optimole.com\/w:768\/h:768\/q:mauto\/f:best\/https:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/08\/Gemini_Generated_Image_m4m99rm4m99rm4m9.png 768w, https:\/\/ml6vmqguit1n.i.optimole.com\/w:1536\/h:1536\/q:mauto\/f:best\/https:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/08\/Gemini_Generated_Image_m4m99rm4m99rm4m9.png 1536w, https:\/\/ml6vmqguit1n.i.optimole.com\/w:1920\/h:1920\/q:mauto\/f:best\/https:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/08\/Gemini_Generated_Image_m4m99rm4m99rm4m9.png 2048w\" sizes=\"(max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n<\/div>\n\n\n<p>1<\/p>\n\n\n\n<p><\/p>\n\n\n\n<p>2<\/p>\n\n\n\n<p><\/p>\n\n\n\n<div data-wp-interactive=\"core\/file\" class=\"wp-block-file\"><object data-wp-bind--hidden=\"!state.hasPdfPreview\" hidden class=\"wp-block-file__embed\" data=\"https:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/08\/Unleashing-GPU-Sharing-for-Cost-Efficient-Multi-LLM-Serving-2505.04021v2.pdf\" type=\"application\/pdf\" style=\"width:100%;height:620px\" aria-label=\"Embed of Unleashing GPU Sharing for Cost-Efficient Multi-LLM Serving 2505.04021v2.\"><\/object><a id=\"wp-block-file--media-bbc80e8b-690d-4354-886d-7e3857828574\" href=\"https:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/08\/Unleashing-GPU-Sharing-for-Cost-Efficient-Multi-LLM-Serving-2505.04021v2.pdf\">Unleashing GPU Sharing for Cost-Efficient Multi-LLM Serving 2505.04021v2<\/a><a href=\"https:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/08\/Unleashing-GPU-Sharing-for-Cost-Efficient-Multi-LLM-Serving-2505.04021v2.pdf\" class=\"wp-block-file__button wp-element-button\" download aria-describedby=\"wp-block-file--media-bbc80e8b-690d-4354-886d-7e3857828574\">Download<\/a><\/div>\n","protected":false},"excerpt":{"rendered":"<p>1 2<\/p>\n","protected":false},"author":1,"featured_media":2987,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"neve_meta_sidebar":"","neve_meta_container":"","neve_meta_enable_content_width":"","neve_meta_content_width":0,"neve_meta_title_alignment":"","neve_meta_author_avatar":"","neve_post_elements_order":"","neve_meta_disable_header":"","neve_meta_disable_footer":"","neve_meta_disable_title":"","footnotes":""},"categories":[10],"tags":[],"class_list":["post-2984","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-signal_scythe"],"_links":{"self":[{"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=\/wp\/v2\/posts\/2984","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=2984"}],"version-history":[{"count":1,"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=\/wp\/v2\/posts\/2984\/revisions"}],"predecessor-version":[{"id":2988,"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=\/wp\/v2\/posts\/2984\/revisions\/2988"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=\/wp\/v2\/media\/2987"}],"wp:attachment":[{"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=2984"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=2984"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=2984"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}