[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117252-en":3,"doc-seo-117252-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},117252,8796095462418,"Noah","https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780",8,"Research & Report","Evaluating Serverless Machine Learning Performance on Google Cloud Run - 1st Prerana Khatiwada - Abstract","End-users can obtain functions-as-a-Service from serverless platforms that offer lower hosting cost, high availability, fault tolerance, and dynamic flexibility for microservices. Machine learning services are increasingly demanded at scale, and serverless platforms can host them through cost efficiency, resource scaling, robust APIs, and global reach. This study evaluates how Google Cloud Run handles machine learning workloads, highlighting that it is GPU-less and not intended for machine learning deployment.","Evaluating Serverless Machine Learning Performance on Google Cloud Run  \n1st Prerana Khatiwada  \nComputer and Information Sciences University of Delaware Newark, United States [preranak@udel.edu](preranak@udel.edu)  \n2nd Pranjal Dhakal  \nComputer and Information Sciences University of Delaware Newark, United States [dpranjal@udel.edu](dpranjal@udel.edu)  \nAbstract—End-users can get functions-as-a-Service from serverless platforms, which promise lower hosting costs, high availability, fault tolerance, and dynamic flexibility for hosting individual functions known as microservices. Machine learning tools are seen to be reliably useful, and the services created using these tools are in increasing demand on a large scale. The serverless platforms are uniquely suited for hosting these machine learning services to be used for large-scale applications. These platforms are well known for their cost efficiency, fault tolerance, resource scaling, robust APIs for communication, and global reach. However, machine learning services are different from the web-services in that these serverless platforms were originally designed to host web services. We aimed to understand how these serverless platforms handle machine learning workloads with our study. We examine machine learning performance on one of the serverless platforms - Google Cloud Run which is a GPU-less infrastructure that is not designed for machine learning application deployment.  \nIndex Terms—Microservice, Flask, Cloud, Deploy, Machine Learning  \nI. INTRODUCTION  \nServerless computing platforms eliminate and minimize the need for expensive onsite hardware, software, and storage infrastructure. These platforms run containerized applications, which are very costeffective. Therefore, it’s important to know how to package such applications as containers and to be familiar with some of the technical terms we’ll come across while working on this project. Through this project, we aim to understand microservice architecture, which is an increasingly popular approach to software development. The below section provides a more detailed description of the terms that are commonly used for this project and are discussed further in the rest ofthe section.  \nMachine learning applications are commonly deployed in servers with GPUs, which are very costly. These GPU-enabled platforms offer a limited set of services compared to serverless platforms like Google Cloud Platform or Amazon Web Services. Thus, the goal of this study is to understand how machine learning web applications perform in serverless platforms that aren’t yet optimized for this sort of workload.  \nA. Containers  \nA container is an executable entity consisting of software code along with the operating system libraries and dependen-  \ncies required to run the code and it enables applications to run almost anywhere. The process of creating containers is called containerization [1] . Containers are portable and are extensively used for developing modern cloud applications. Containers virtualize the operating system, allowing them to run anywhere from a private datacenter to the public cloud, or even on a developer’s laptop. Everything at Google runs in containers, from Gmail to YouTube to Search [2] .  \nContainers and virtual machines are comparable in that they promote IT efficiency and DevOps. However understanding difference between them is critical to build a cloud native approach.A virtual machine has a guest operating system, a virtual copy of the hardware that the operating system needs to run, and an application with its associated libraries and depen-dencies [3].Unlike a virtual machine, containers do not need to include the guest operating system in every single instance, instead it can leverage the features and resources of the host operating system so that each individual container contains only the applications and its libraries and dependencies.  \nB. Docker  \nThe host machine (server) where the containers are ex-ecuted","cbCails1mRWia9M6","https://ap.wps.com/l/cbCails1mRWia9M6","pdf",451107,1,5,"English","en",105,"# Introduction\n## Containers\n## Docker\n## REST API\n## Google Cloud Run","[{\"question\":\"What problem does this study address for serverless machine learning?\",\"answer\":\"It investigates how serverless platforms designed for web services handle machine learning workloads, especially when the platform is not optimized for ML deployment.\"},{\"question\":\"Why is Google Cloud Run central to the evaluation?\",\"answer\":\"The study focuses on Google Cloud Run because it runs containerized applications with automatic scaling, while being GPU-less and not originally intended for machine learning deployment.\"},{\"question\":\"How do microservices communicate in the described architecture?\",\"answer\":\"Microservices communicate using REST APIs, where REST defines rules for sending and receiving data and can be implemented using HTTP requests.\"}]","Evaluating Serverless Machine Learning Performance on Google Cloud Run - 1st Prerana Khatiwada - Abstract | PDF",1785674704,13,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"evaluating-serverless-machine-learning-performance-on-google-cloud-run-1st-prerana-khatiwada-abstract","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/evaluating-serverless-machine-learning-performance-on-google-cloud-run-1st-prerana-khatiwada-abstract/117252/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05","2026-08-02",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does this study address for serverless machine learning?","Question",{"text":76,"@type":77},"It investigates how serverless platforms designed for web services handle machine learning workloads, especially when the platform is not optimized for ML deployment.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Why is Google Cloud Run central to the evaluation?",{"text":81,"@type":77},"The study focuses on Google Cloud Run because it runs containerized applications with automatic scaling, while being GPU-less and not originally intended for machine learning deployment.",{"name":83,"@type":74,"acceptedAnswer":84},"How do microservices communicate in the described architecture?",{"text":85,"@type":77},"Microservices communicate using REST APIs, where REST defines rules for sending and receiving data and can be implemented using HTTP requests.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":21,"slug":138},19,"General","general"]