This document discusses various options for deploying machine learning models including AWS Lambda, Kubernetes, KServe (previously known as Kubeflow Serving), and AWS SageMaker. It provides an overview of deploying models with Kubernetes using Deployments and Services. Specific examples are given for deploying Keras models with TensorFlow Serving and a gateway using gRPC as well as deploying with KServe including the use of transformers. The document concludes that there is no one size fits all solution and different options may be better suited depending on factors like load size, ease of use, transparency, and cost.
Deploying deep learning models with Kubernetes and KubeflowDataPhoenix
Третий технический вебинар из серии "The A-Z of Data", который посвящен деплою DL моделей при помощи Kubernetes и Kubeflow.
https://dataphoenix.info/webinar-deploying-deep-learning-models-with-kubernetes-and-kubeflow/
В этом докладе вы узнаете про деплой Keras моделей. Сначала мы увидим, как это сделать с помощью TF-Serving и Kubernetes, а во второй части выступления мы сделаем это с помощью KFServing и Kubeflow.
Спикер:
Алексей Григорьев - Principal Data Scientist в OLX Group, основатель DataTalks.Club. Алексей написал несколько книг о машинном обучении. Одной из них является Machine Learning Bookcamp - книга для программистов, которые хотят заняться машинным обучением.
Подписывайтесь на наш Telegram канал (https://t.me/DataPhoenix), чтобы всегда быть в курсе последних новостей!
"The A-Z of Data" (https://dataphoenix.info/the-a-z-of-data) - серия вебинаров от команды Data Phoenix Events, в рамках которых вы сможете систематизировать и расширить свои знания работы с данными. Все вебинары будут разбиты на тематические блоки, а каждый блок будет состоять из обзорного вебинара, нескольких технических вебинаров про лучшие инструменты/практики/подходы/архитектуры моделей, а также вебинара с практическими юзкейсами и дискуссионной панелью экспертов. До конца 2021 года мы планируем раскрыть такие темы как: MLOps, Natural Language Processing, Computer Vision и Time-Series Forecasting.
OpenShift Meetup - Tokyo - Service Mesh and Serverless OverviewMaría Angélica Bracho
This document provides an overview of service mesh and serverless technologies. It discusses the evolution of microservices and how service mesh addresses needs like service discovery, routing and monitoring. It introduces concepts like sidecars and shows the architecture of Istio service mesh. It then defines serverless computing and discusses how the Knative project implements a serverless platform on Kubernetes. It shows examples of using Knative to deploy serverless applications on OpenShift and highlights the roadmap for integrating technologies like Tekton.
Serverless Machine Learning Model Inference on Kubernetes with KServe.pdfStavros Kontopoulos
This document discusses serverless machine learning model inference using KServe on Kubernetes. It describes how KServe provides a control plane for deploying, scaling and managing machine learning models. Key features of KServe include supporting popular machine learning frameworks, autoscaling for traffic bursts, preprocessing/postprocessing, GPU support, HTTP/gRPC endpoints, deployment strategies like canary rollouts, batch inference and integration with feature stores. KServe integrates with Knative Serving for a serverless layer, and provides runtimes, monitoring, logging and inference graphs to connect multiple models for machine learning pipelines. Examples demonstrate single model serving, autoscaling, canary deployments and load testing with KServe and Kubernetes.
How can you accelerate the delivery of new, high-quality services? How can you be able to experiment and get feedback quickly from your customers? To get the most out of the agility afforded by serverless and containers, it is essential to build CI/CD pipelines that help teams iterate on code and quickly release features. In this talk, we demonstrate how developers can build effective CI/CD release workflows to manage their serverless or containerized deployments on AWS. We cover infrastructure-as-code (IaC) application models, such as AWS Serverless Application Model (AWS SAM) and new imperative IaC tools. We also demonstrate how to set up CI/CD release pipelines with AWS CodePipeline and AWS CodeBuild, and we show you how to automate safer deployments with AWS CodeDeploy.
Amazon Elastic Kubernetes Service (Amazon EKS) is a fully-managed, certified Kubernetes conformant service that simplifies the process of building, securing, operating, and maintaining Kubernetes clusters on AWS
https://thinkcloudly.com/?s=aws+Elastic+Kubernetes+Service+
Node Interactive: Node.js Performance and Highly Scalable Micro-ServicesChris Bailey
The fundamental performance characteristics of Node.js, along with the improvements driven through the community benchmarking workgroup, makes Node.js ideal for highly performing micro-service workloads. Translating that into highly responsive, scalable solutions however is still far from easy. This session will discuss why Node.js is right for micro-services, introduce the best practices for building scalable deployments, and show you how to monitor and profile your applications to identify and resolve performance bottlenecks.
Continuous Integration e Delivery per (r)innovare lo sviluppo software e la g...Amazon Web Services
This document discusses continuous integration and delivery practices using AWS services like CodeCommit, CodeBuild, CodeDeploy, and CodePipeline. It summarizes how these services can be used together in a software development pipeline to automate building, testing, and deploying code changes. It also discusses how infrastructure as code with CloudFormation templates allows infrastructure to be provisioned and managed like code. The document provides an example of how a company implemented continuous integration of their infrastructure stacks using CloudFormation across different environments.
Deploying deep learning models with Kubernetes and KubeflowDataPhoenix
Третий технический вебинар из серии "The A-Z of Data", который посвящен деплою DL моделей при помощи Kubernetes и Kubeflow.
https://dataphoenix.info/webinar-deploying-deep-learning-models-with-kubernetes-and-kubeflow/
В этом докладе вы узнаете про деплой Keras моделей. Сначала мы увидим, как это сделать с помощью TF-Serving и Kubernetes, а во второй части выступления мы сделаем это с помощью KFServing и Kubeflow.
Спикер:
Алексей Григорьев - Principal Data Scientist в OLX Group, основатель DataTalks.Club. Алексей написал несколько книг о машинном обучении. Одной из них является Machine Learning Bookcamp - книга для программистов, которые хотят заняться машинным обучением.
Подписывайтесь на наш Telegram канал (https://t.me/DataPhoenix), чтобы всегда быть в курсе последних новостей!
"The A-Z of Data" (https://dataphoenix.info/the-a-z-of-data) - серия вебинаров от команды Data Phoenix Events, в рамках которых вы сможете систематизировать и расширить свои знания работы с данными. Все вебинары будут разбиты на тематические блоки, а каждый блок будет состоять из обзорного вебинара, нескольких технических вебинаров про лучшие инструменты/практики/подходы/архитектуры моделей, а также вебинара с практическими юзкейсами и дискуссионной панелью экспертов. До конца 2021 года мы планируем раскрыть такие темы как: MLOps, Natural Language Processing, Computer Vision и Time-Series Forecasting.
OpenShift Meetup - Tokyo - Service Mesh and Serverless OverviewMaría Angélica Bracho
This document provides an overview of service mesh and serverless technologies. It discusses the evolution of microservices and how service mesh addresses needs like service discovery, routing and monitoring. It introduces concepts like sidecars and shows the architecture of Istio service mesh. It then defines serverless computing and discusses how the Knative project implements a serverless platform on Kubernetes. It shows examples of using Knative to deploy serverless applications on OpenShift and highlights the roadmap for integrating technologies like Tekton.
Serverless Machine Learning Model Inference on Kubernetes with KServe.pdfStavros Kontopoulos
This document discusses serverless machine learning model inference using KServe on Kubernetes. It describes how KServe provides a control plane for deploying, scaling and managing machine learning models. Key features of KServe include supporting popular machine learning frameworks, autoscaling for traffic bursts, preprocessing/postprocessing, GPU support, HTTP/gRPC endpoints, deployment strategies like canary rollouts, batch inference and integration with feature stores. KServe integrates with Knative Serving for a serverless layer, and provides runtimes, monitoring, logging and inference graphs to connect multiple models for machine learning pipelines. Examples demonstrate single model serving, autoscaling, canary deployments and load testing with KServe and Kubernetes.
How can you accelerate the delivery of new, high-quality services? How can you be able to experiment and get feedback quickly from your customers? To get the most out of the agility afforded by serverless and containers, it is essential to build CI/CD pipelines that help teams iterate on code and quickly release features. In this talk, we demonstrate how developers can build effective CI/CD release workflows to manage their serverless or containerized deployments on AWS. We cover infrastructure-as-code (IaC) application models, such as AWS Serverless Application Model (AWS SAM) and new imperative IaC tools. We also demonstrate how to set up CI/CD release pipelines with AWS CodePipeline and AWS CodeBuild, and we show you how to automate safer deployments with AWS CodeDeploy.
Amazon Elastic Kubernetes Service (Amazon EKS) is a fully-managed, certified Kubernetes conformant service that simplifies the process of building, securing, operating, and maintaining Kubernetes clusters on AWS
https://thinkcloudly.com/?s=aws+Elastic+Kubernetes+Service+
Node Interactive: Node.js Performance and Highly Scalable Micro-ServicesChris Bailey
The fundamental performance characteristics of Node.js, along with the improvements driven through the community benchmarking workgroup, makes Node.js ideal for highly performing micro-service workloads. Translating that into highly responsive, scalable solutions however is still far from easy. This session will discuss why Node.js is right for micro-services, introduce the best practices for building scalable deployments, and show you how to monitor and profile your applications to identify and resolve performance bottlenecks.
Continuous Integration e Delivery per (r)innovare lo sviluppo software e la g...Amazon Web Services
This document discusses continuous integration and delivery practices using AWS services like CodeCommit, CodeBuild, CodeDeploy, and CodePipeline. It summarizes how these services can be used together in a software development pipeline to automate building, testing, and deploying code changes. It also discusses how infrastructure as code with CloudFormation templates allows infrastructure to be provisioned and managed like code. The document provides an example of how a company implemented continuous integration of their infrastructure stacks using CloudFormation across different environments.
IBM Cloud University: Build, Deploy and Scale Node.js MicroservicesChris Bailey
The document discusses key aspects of building scalable microservices including containerization, orchestration, monitoring, and performance optimization. It provides code examples for containerizing a Node.js application, deploying it with Kubernetes using a Helm chart, and implementing continuous delivery with Jenkins pipelines and DevOps toolchains. The document also covers understanding microservices performance by analyzing architecture diagrams showing public/private networks, services, and databases.
Advanced Model Inferencing leveraging Kubeflow Serving, KNative and IstioAnimesh Singh
Model Inferencing use cases are becoming a requirement for models moving into the next phase of production deployments. More and more users are now encountering use cases around canary deployments, scale-to-zero or serverless characteristics. And then there are also advanced use cases coming around model explainability, including A/B tests, ensemble models, multi-armed bandits, etc.
In this talk, the speakers are going to detail how to handle these use cases using Kubeflow Serving and the native Kubernetes stack which is Istio and Knative. Knative and Istio help with autoscaling, scale-to-zero, canary deployments to be implemented, and scenarios where traffic is optimized to the best performing models. This can be combined with KNative eventing, Istio observability stack, KFServing Transformer to handle pre/post-processing and payload logging which consequentially can enable drift and outlier detection to be deployed. We will demonstrate where currently KFServing is, and where it's heading towards.
The document provides an overview of Kubernetes including its introduction, configuration file creation using direct editing, templates with Helm and Kustomize, usage patterns, web service practices, and deployment pipelines. Key sections include explaining Kubernetes architecture and mechanisms, setting up access to a Kubernetes cluster, generating Helm templates to render Kubernetes objects, customizing templates for different environments in Kustomize, and using ArgoCD for deployment automation.
The slides used during the mlops.community meetup on KFServing. We looked inside some popular model formats like the SavedModel of Tensorflow and the Model Archiver of PyTorch, to understand how the weights of the NN are saved there, the graph and the signature concepts. We discussed the relevant resources of the deployment stack of Istio (the ingress gateway, the sidecar and the virtual service) and Knative (the service and revisions), as well as Kubeflow and KFServing. Then we got into the design details of KFServing, its custom resources, its controller. Then we spent some time to discuss the monitoring stack, the metrics of the servable as well as the model metrics which end up to Prometheus. We looked at the inference payload and prediction logging to observe drifts and trigger the retraining of the pipeline. Finally, a few words about the awesome community and the roadmap of the project on multi-model serving and inference routing graph.
The document provides an overview of application lifecycle management (ALM) in a serverless world. It discusses key concepts like continuous integration/delivery and testing practices for serverless applications. Serverless architectures using AWS Lambda and API Gateway are highlighted, along with how to manage deployments, configurations, and monitor applications.
This document provides an agenda and overview for a webinar on Kubernetes. The agenda includes an introduction to Kabisa, an introduction to Kubernetes concepts, and a hands-on Kubernetes workshop. Kabisa is introduced as a software development agency specialized in custom web and mobile app development with over 14 years of experience. Key Kubernetes concepts are then summarized, including clusters, nodes, pods, namespaces, replica sets, load balancers, and deployments. Finally, the hands-on workshop is outlined which will have participants claim a Kubernetes cluster and complete tasks like creating pods, services, and using deployments, environment variables, secrets, and config maps.
The document provides steps to connect to a CloudFoundry environment and deploy a sample Predix application. It includes instructions on installing the CF CLI, logging in, listing services, creating a PostgreSQL service instance, pushing a sample app, and binding the app to the database. The steps cover common operations for deploying and managing apps on Pivotal CloudFoundry and interacting with services on Predix.
Cloud Foundry Summit Europe 2018 - Deveveloper Experience with Cloud Foundry ...Neven Cvetković
What's the difference between these platforms, what do they have in common, and what does working with each of them look like from a developer perspective? Landing your code on the right platform will determine the quality of your developer experience. It's important, therefore, to understand what kinds of workloads are most suitable for each, the level of effort required to work with them, and what each platform does for you.
Do you let buildpacks create containers for you, or do you build your own? How much YAML do you need to author and maintain? What kind of security can your application expect from the platform?
You'll leave this session with a clear understanding of what two platforms do for developers.
Hybrid Cloud, Kubeflow and Tensorflow Extended [TFX]Animesh Singh
Kubeflow Pipelines and TensorFlow Extended (TFX) together is end-to-end platform for deploying production ML pipelines. It provides a configuration framework and shared libraries to integrate common components needed to define, launch, and monitor your machine learning system. In this talk we describe how how to run TFX in hybrid cloud environments.
Deploying Cloud Native Red Team Infrastructure with Kubernetes, Istio and Envoy Jeffrey Holden
This document discusses deploying cloud native red team infrastructure using Kubernetes, Istio and Envoy. It provides introductions to Larry Suto and Jeff Holden and their backgrounds. It then covers goals of being automated, portable and scriptable. Key points covered include using Kubernetes for its infrastructure as code capabilities. It discusses concepts like Docker, Kubernetes, Kops, External DNS, SSL Cert Manager and recipes for containerizing tools like Cobalt Strike, Merlin and configuring deployments.
Designing a production grade realtime ml inference endpointChandim Sett
This presentation discusses about designing a ML inference endpoint application in python flask and Docker containers using appropriate software engineering design principles. The application being developed is an enterprise production grade.
Get you Java application ready for Kubernetes !Anthony Dahanne
In this demos loaded talk we’ll explore the best practices to create a Docker image for a Java app (it’s 2019 and new comers such as Jib, CNCF buildpacks are interesting alternatives to Docker builds !) - and how to integrate best with the Kubernetes ecosystem : after explaining main Kubernetes objects and notions, we’ll discuss Helm charts and productivity tools such as Skaffold, Draft and Telepresence.
Cloud Native Night, April 2018, Mainz: Workshop led by Jörg Schad (@joerg_schad, Technical Community Lead / Developer at Mesosphere)
Join our Meetup: https://www.meetup.com/de-DE/Cloud-Native-Night/
PLEASE NOTE:
During this workshop, Jörg showed many demos and the audience could participate on their laptops. Unfortunately, we can't provide these demos. Nevertheless, Jörg's slides give a deep dive into the topic.
DETAILS ABOUT THE WORKSHOP:
Kubernetes has been one of the topics in 2017 and will probably remain so in 2018. In this hands-on technical workshop you will learn how best to deploy, operate and scale Kubernetes clusters from one to hundreds of nodes using DC/OS. You will learn how to integrate and run Kubernetes alongside traditional applications and fast data services of your choice (e.g. Apache Cassandra, Apache Kafka, Apache Spark, TensorFlow and more) on any infrastructure.
This workshop best suits operators focussed on keeping their apps and services up and running in production and developers focussed on quickly delivering internal and customer facing apps into production.
You will learn how to:
- Introduction to Kubernetes and DC/OS (including the differences between both)
- Deploy Kubernetes on DC/OS in a secure, highly available, and fault-tolerant manner
- Solve operational challenges of running a large/multiple Kubernetes cluster
- One-click deploy big data stateful and stateless services alongside a Kubernetes cluster
The “Twelve-Factor” application model has come to represent twelve best practices for building modern, cloud-native applications. With guidance on things like configuration, deployment, runtime, and multiple service communication, the Twelve-Factor model prescribes best practices that apply to everything from web applications to APIs to data processing applications.
Although serverless computing and AWS Lambda have changed how application development is done, the “Twelve-Factor” best practices remain relevant and applicable in a serverless world. In this talk, Chris will share with you how to apply the “Twelve-Factor” model to serverless application development with AWS Lambda and Amazon API Gateway and show you how these services enable you to build scalable, low cost, and low administration applications.
This document provides an overview of serverless applications and how to build one. It discusses what serverless means, common use cases, how to bundle and deploy code, continuous integration and delivery, versioning, monitoring, and more. Specific AWS services for building serverless applications are also covered, including AWS Lambda, API Gateway, DynamoDB, S3, CloudFormation, CodeBuild, CodePipeline, X-Ray and CloudWatch.
Simplify Cloud Applications using Spring CloudRamnivas Laddad
This document discusses how to simplify cloud applications using Spring Cloud. It describes Spring Cloud's goals of abstracting over cloud services and environments. It covers using Java and XML configuration, scanning for services, and acquiring services. It also discusses Spring Cloud's extensibility for cloud platforms, services, and frameworks. The document includes demos of using Spring Cloud on Cloud Foundry, Heroku, and with Hadoop. It describes the integration with Spring Boot.
12 Factor Serverless Applications - Mike Morain, AWS - Cloud Native Day Tel A...Cloud Native Day Tel Aviv
The “Twelve-Factor” application model has come to represent twelve best practices for building modern, cloud-native applications. With guidance on things like configuration, deployment, runtime, and multiple service communication, the Twelve-Factor model prescribes best practices that apply to everything from web applications to APIs to data processing applications. Although Serverless computing and AWS Lambda have changed how application development is done, the “Twelve-Factor” best practices remain relevant and applicable in a Serverless world. In this talk, we’ll apply the “Twelve-Factor” model to Serverless application development with AWS Lambda and Amazon API Gateway and show you how these services enable you to build scalable, low cost, and low administration applications.
Kubernetes Overview - Deploy your app with confidenceOmer Barel
Kubernetes is an open source system for managing containerized applications across multiple hosts that provides mechanisms for deploying, maintaining, and scaling applications. It uses concepts like pods, deployments, services, configmaps and secrets to deploy and manage applications. Key features include portability across infrastructure providers, self-healing capabilities, and enabling developers to focus on building applications without worrying about operations.
Exploring Infrastructure Management for GenAI Beyond KubernetesDataPhoenix
During this talk, we will discuss the Kubernetes stack's drawbacks in the context of AI and show how dstack addresses them in the training and deployment of GenAI models.
Recording of the webinar: https://dataphoenix.info/exploring-infrastructure-management-for-genai-beyond-kubernetes/
ODS.ai Odessa Meetup #4: NLP: изменения за последние 10 летDataPhoenix
Philip Marchenko (Machine Learning Expert at 3DLOOK)
В этом докладе не будет никакой научной новизны, в нем нет никаких лайфхаков etc. Это будет, скорее, нечто ретроспективное: мы постараемся отследить, как изменялся тренд в nlp за последние 10 лет и разберёмся с самыми хайповыми моделями.
https://dataphoenix.info/ods-ai-odessa-meetup-4/
Видео: https://youtu.be/WN6Y1J06fy4
Подписывайтесь на наш Telegram канал (https://t.me/DataPhoenix), чтобы всегда быть в курсе последних новостей!
More Related Content
Similar to Deploying DL models with Kubernetes and Kubeflow
IBM Cloud University: Build, Deploy and Scale Node.js MicroservicesChris Bailey
The document discusses key aspects of building scalable microservices including containerization, orchestration, monitoring, and performance optimization. It provides code examples for containerizing a Node.js application, deploying it with Kubernetes using a Helm chart, and implementing continuous delivery with Jenkins pipelines and DevOps toolchains. The document also covers understanding microservices performance by analyzing architecture diagrams showing public/private networks, services, and databases.
Advanced Model Inferencing leveraging Kubeflow Serving, KNative and IstioAnimesh Singh
Model Inferencing use cases are becoming a requirement for models moving into the next phase of production deployments. More and more users are now encountering use cases around canary deployments, scale-to-zero or serverless characteristics. And then there are also advanced use cases coming around model explainability, including A/B tests, ensemble models, multi-armed bandits, etc.
In this talk, the speakers are going to detail how to handle these use cases using Kubeflow Serving and the native Kubernetes stack which is Istio and Knative. Knative and Istio help with autoscaling, scale-to-zero, canary deployments to be implemented, and scenarios where traffic is optimized to the best performing models. This can be combined with KNative eventing, Istio observability stack, KFServing Transformer to handle pre/post-processing and payload logging which consequentially can enable drift and outlier detection to be deployed. We will demonstrate where currently KFServing is, and where it's heading towards.
The document provides an overview of Kubernetes including its introduction, configuration file creation using direct editing, templates with Helm and Kustomize, usage patterns, web service practices, and deployment pipelines. Key sections include explaining Kubernetes architecture and mechanisms, setting up access to a Kubernetes cluster, generating Helm templates to render Kubernetes objects, customizing templates for different environments in Kustomize, and using ArgoCD for deployment automation.
The slides used during the mlops.community meetup on KFServing. We looked inside some popular model formats like the SavedModel of Tensorflow and the Model Archiver of PyTorch, to understand how the weights of the NN are saved there, the graph and the signature concepts. We discussed the relevant resources of the deployment stack of Istio (the ingress gateway, the sidecar and the virtual service) and Knative (the service and revisions), as well as Kubeflow and KFServing. Then we got into the design details of KFServing, its custom resources, its controller. Then we spent some time to discuss the monitoring stack, the metrics of the servable as well as the model metrics which end up to Prometheus. We looked at the inference payload and prediction logging to observe drifts and trigger the retraining of the pipeline. Finally, a few words about the awesome community and the roadmap of the project on multi-model serving and inference routing graph.
The document provides an overview of application lifecycle management (ALM) in a serverless world. It discusses key concepts like continuous integration/delivery and testing practices for serverless applications. Serverless architectures using AWS Lambda and API Gateway are highlighted, along with how to manage deployments, configurations, and monitor applications.
This document provides an agenda and overview for a webinar on Kubernetes. The agenda includes an introduction to Kabisa, an introduction to Kubernetes concepts, and a hands-on Kubernetes workshop. Kabisa is introduced as a software development agency specialized in custom web and mobile app development with over 14 years of experience. Key Kubernetes concepts are then summarized, including clusters, nodes, pods, namespaces, replica sets, load balancers, and deployments. Finally, the hands-on workshop is outlined which will have participants claim a Kubernetes cluster and complete tasks like creating pods, services, and using deployments, environment variables, secrets, and config maps.
The document provides steps to connect to a CloudFoundry environment and deploy a sample Predix application. It includes instructions on installing the CF CLI, logging in, listing services, creating a PostgreSQL service instance, pushing a sample app, and binding the app to the database. The steps cover common operations for deploying and managing apps on Pivotal CloudFoundry and interacting with services on Predix.
Cloud Foundry Summit Europe 2018 - Deveveloper Experience with Cloud Foundry ...Neven Cvetković
What's the difference between these platforms, what do they have in common, and what does working with each of them look like from a developer perspective? Landing your code on the right platform will determine the quality of your developer experience. It's important, therefore, to understand what kinds of workloads are most suitable for each, the level of effort required to work with them, and what each platform does for you.
Do you let buildpacks create containers for you, or do you build your own? How much YAML do you need to author and maintain? What kind of security can your application expect from the platform?
You'll leave this session with a clear understanding of what two platforms do for developers.
Hybrid Cloud, Kubeflow and Tensorflow Extended [TFX]Animesh Singh
Kubeflow Pipelines and TensorFlow Extended (TFX) together is end-to-end platform for deploying production ML pipelines. It provides a configuration framework and shared libraries to integrate common components needed to define, launch, and monitor your machine learning system. In this talk we describe how how to run TFX in hybrid cloud environments.
Deploying Cloud Native Red Team Infrastructure with Kubernetes, Istio and Envoy Jeffrey Holden
This document discusses deploying cloud native red team infrastructure using Kubernetes, Istio and Envoy. It provides introductions to Larry Suto and Jeff Holden and their backgrounds. It then covers goals of being automated, portable and scriptable. Key points covered include using Kubernetes for its infrastructure as code capabilities. It discusses concepts like Docker, Kubernetes, Kops, External DNS, SSL Cert Manager and recipes for containerizing tools like Cobalt Strike, Merlin and configuring deployments.
Designing a production grade realtime ml inference endpointChandim Sett
This presentation discusses about designing a ML inference endpoint application in python flask and Docker containers using appropriate software engineering design principles. The application being developed is an enterprise production grade.
Get you Java application ready for Kubernetes !Anthony Dahanne
In this demos loaded talk we’ll explore the best practices to create a Docker image for a Java app (it’s 2019 and new comers such as Jib, CNCF buildpacks are interesting alternatives to Docker builds !) - and how to integrate best with the Kubernetes ecosystem : after explaining main Kubernetes objects and notions, we’ll discuss Helm charts and productivity tools such as Skaffold, Draft and Telepresence.
Cloud Native Night, April 2018, Mainz: Workshop led by Jörg Schad (@joerg_schad, Technical Community Lead / Developer at Mesosphere)
Join our Meetup: https://www.meetup.com/de-DE/Cloud-Native-Night/
PLEASE NOTE:
During this workshop, Jörg showed many demos and the audience could participate on their laptops. Unfortunately, we can't provide these demos. Nevertheless, Jörg's slides give a deep dive into the topic.
DETAILS ABOUT THE WORKSHOP:
Kubernetes has been one of the topics in 2017 and will probably remain so in 2018. In this hands-on technical workshop you will learn how best to deploy, operate and scale Kubernetes clusters from one to hundreds of nodes using DC/OS. You will learn how to integrate and run Kubernetes alongside traditional applications and fast data services of your choice (e.g. Apache Cassandra, Apache Kafka, Apache Spark, TensorFlow and more) on any infrastructure.
This workshop best suits operators focussed on keeping their apps and services up and running in production and developers focussed on quickly delivering internal and customer facing apps into production.
You will learn how to:
- Introduction to Kubernetes and DC/OS (including the differences between both)
- Deploy Kubernetes on DC/OS in a secure, highly available, and fault-tolerant manner
- Solve operational challenges of running a large/multiple Kubernetes cluster
- One-click deploy big data stateful and stateless services alongside a Kubernetes cluster
The “Twelve-Factor” application model has come to represent twelve best practices for building modern, cloud-native applications. With guidance on things like configuration, deployment, runtime, and multiple service communication, the Twelve-Factor model prescribes best practices that apply to everything from web applications to APIs to data processing applications.
Although serverless computing and AWS Lambda have changed how application development is done, the “Twelve-Factor” best practices remain relevant and applicable in a serverless world. In this talk, Chris will share with you how to apply the “Twelve-Factor” model to serverless application development with AWS Lambda and Amazon API Gateway and show you how these services enable you to build scalable, low cost, and low administration applications.
This document provides an overview of serverless applications and how to build one. It discusses what serverless means, common use cases, how to bundle and deploy code, continuous integration and delivery, versioning, monitoring, and more. Specific AWS services for building serverless applications are also covered, including AWS Lambda, API Gateway, DynamoDB, S3, CloudFormation, CodeBuild, CodePipeline, X-Ray and CloudWatch.
Simplify Cloud Applications using Spring CloudRamnivas Laddad
This document discusses how to simplify cloud applications using Spring Cloud. It describes Spring Cloud's goals of abstracting over cloud services and environments. It covers using Java and XML configuration, scanning for services, and acquiring services. It also discusses Spring Cloud's extensibility for cloud platforms, services, and frameworks. The document includes demos of using Spring Cloud on Cloud Foundry, Heroku, and with Hadoop. It describes the integration with Spring Boot.
12 Factor Serverless Applications - Mike Morain, AWS - Cloud Native Day Tel A...Cloud Native Day Tel Aviv
The “Twelve-Factor” application model has come to represent twelve best practices for building modern, cloud-native applications. With guidance on things like configuration, deployment, runtime, and multiple service communication, the Twelve-Factor model prescribes best practices that apply to everything from web applications to APIs to data processing applications. Although Serverless computing and AWS Lambda have changed how application development is done, the “Twelve-Factor” best practices remain relevant and applicable in a Serverless world. In this talk, we’ll apply the “Twelve-Factor” model to Serverless application development with AWS Lambda and Amazon API Gateway and show you how these services enable you to build scalable, low cost, and low administration applications.
Kubernetes Overview - Deploy your app with confidenceOmer Barel
Kubernetes is an open source system for managing containerized applications across multiple hosts that provides mechanisms for deploying, maintaining, and scaling applications. It uses concepts like pods, deployments, services, configmaps and secrets to deploy and manage applications. Key features include portability across infrastructure providers, self-healing capabilities, and enabling developers to focus on building applications without worrying about operations.
Similar to Deploying DL models with Kubernetes and Kubeflow (20)
Exploring Infrastructure Management for GenAI Beyond KubernetesDataPhoenix
During this talk, we will discuss the Kubernetes stack's drawbacks in the context of AI and show how dstack addresses them in the training and deployment of GenAI models.
Recording of the webinar: https://dataphoenix.info/exploring-infrastructure-management-for-genai-beyond-kubernetes/
ODS.ai Odessa Meetup #4: NLP: изменения за последние 10 летDataPhoenix
Philip Marchenko (Machine Learning Expert at 3DLOOK)
В этом докладе не будет никакой научной новизны, в нем нет никаких лайфхаков etc. Это будет, скорее, нечто ретроспективное: мы постараемся отследить, как изменялся тренд в nlp за последние 10 лет и разберёмся с самыми хайповыми моделями.
https://dataphoenix.info/ods-ai-odessa-meetup-4/
Видео: https://youtu.be/WN6Y1J06fy4
Подписывайтесь на наш Telegram канал (https://t.me/DataPhoenix), чтобы всегда быть в курсе последних новостей!
ODS.ai Odessa Meetup #4: Чему учит нас участите в соревновательном MLDataPhoenix
Eugene Khvedchenia (Senior Research Engineer)
Как выиграть соревнование за две недели. А потом проиграть.
https://dataphoenix.info/ods-ai-odessa-meetup-4/
Видео: https://youtu.be/VjOAe_tFV_g
Подписывайтесь на наш Telegram канал (https://t.me/DataPhoenix), чтобы всегда быть в курсе последних новостей!
Команда Data Phoenix Events приглашает всех, 17 августа в 19:00, на первый вебинар из серии "The A-Z of Data", который будет посвящен MLOps. В рамках вводного вебинара, мы рассмотрим, что такое MLOps, основные принципы и практики, лучшие инструменты и возможные архитектуры. Мы начнем с простого жизненного цикла разработки ML решений и закончим сложным, максимально автоматизированным, циклом, который нам позволяет реализовать MLOps.
https://dataphoenix.info/the-a-z-of-data/
https://dataphoenix.info/the-a-z-of-data-introduction-to-mlops/
ODS.ai Odessa Meetup #3: Object Detection in the WildDataPhoenix
Borys Tymchenko (Senior ML Research Engineer at VITech)
Поговорим о том, что делать, если из органов зрения есть только IP/CCTV камеры, а хочется детектировать объекты и их свойства.
https://dataphoenix.info/ods-ai-odessa-meetup-3/
ODS.ai Odessa Meetup #3: Enterprise data management - весело или нет?!DataPhoenix
Kirill Sidorov (Head Of Data Management at Autodoc)
Рассмотрим формирование и типы хранилищ с точки зрения организации. От начальных этапов до внедрения data governance. Архитектура, штат, политика.
https://dataphoenix.info/ods-ai-odessa-meetup-3/
Programming Foundation Models with DSPy - Meetup SlidesZilliz
Prompting language models is hard, while programming language models is easy. In this talk, I will discuss the state-of-the-art framework DSPy for programming foundation models with its powerful optimizers and runtime constraint system.
How to Get CNIC Information System with Paksim Ga.pptxdanishmna97
Pakdata Cf is a groundbreaking system designed to streamline and facilitate access to CNIC information. This innovative platform leverages advanced technology to provide users with efficient and secure access to their CNIC details.
Pushing the limits of ePRTC: 100ns holdover for 100 daysAdtran
At WSTS 2024, Alon Stern explored the topic of parametric holdover and explained how recent research findings can be implemented in real-world PNT networks to achieve 100 nanoseconds of accuracy for up to 100 days.
In the rapidly evolving landscape of technologies, XML continues to play a vital role in structuring, storing, and transporting data across diverse systems. The recent advancements in artificial intelligence (AI) present new methodologies for enhancing XML development workflows, introducing efficiency, automation, and intelligent capabilities. This presentation will outline the scope and perspective of utilizing AI in XML development. The potential benefits and the possible pitfalls will be highlighted, providing a balanced view of the subject.
We will explore the capabilities of AI in understanding XML markup languages and autonomously creating structured XML content. Additionally, we will examine the capacity of AI to enrich plain text with appropriate XML markup. Practical examples and methodological guidelines will be provided to elucidate how AI can be effectively prompted to interpret and generate accurate XML markup.
Further emphasis will be placed on the role of AI in developing XSLT, or schemas such as XSD and Schematron. We will address the techniques and strategies adopted to create prompts for generating code, explaining code, or refactoring the code, and the results achieved.
The discussion will extend to how AI can be used to transform XML content. In particular, the focus will be on the use of AI XPath extension functions in XSLT, Schematron, Schematron Quick Fixes, or for XML content refactoring.
The presentation aims to deliver a comprehensive overview of AI usage in XML development, providing attendees with the necessary knowledge to make informed decisions. Whether you’re at the early stages of adopting AI or considering integrating it in advanced XML development, this presentation will cover all levels of expertise.
By highlighting the potential advantages and challenges of integrating AI with XML development tools and languages, the presentation seeks to inspire thoughtful conversation around the future of XML development. We’ll not only delve into the technical aspects of AI-powered XML development but also discuss practical implications and possible future directions.
Dr. Sean Tan, Head of Data Science, Changi Airport Group
Discover how Changi Airport Group (CAG) leverages graph technologies and generative AI to revolutionize their search capabilities. This session delves into the unique search needs of CAG’s diverse passengers and customers, showcasing how graph data structures enhance the accuracy and relevance of AI-generated search results, mitigating the risk of “hallucinations” and improving the overall customer journey.
Maruthi Prithivirajan, Head of ASEAN & IN Solution Architecture, Neo4j
Get an inside look at the latest Neo4j innovations that enable relationship-driven intelligence at scale. Learn more about the newest cloud integrations and product enhancements that make Neo4j an essential choice for developers building apps with interconnected data and generative AI.
GraphSummit Singapore | The Future of Agility: Supercharging Digital Transfor...Neo4j
Leonard Jayamohan, Partner & Generative AI Lead, Deloitte
This keynote will reveal how Deloitte leverages Neo4j’s graph power for groundbreaking digital twin solutions, achieving a staggering 100x performance boost. Discover the essential role knowledge graphs play in successful generative AI implementations. Plus, get an exclusive look at an innovative Neo4j + Generative AI solution Deloitte is developing in-house.
UiPath Test Automation using UiPath Test Suite series, part 6DianaGray10
Welcome to UiPath Test Automation using UiPath Test Suite series part 6. In this session, we will cover Test Automation with generative AI and Open AI.
UiPath Test Automation with generative AI and Open AI webinar offers an in-depth exploration of leveraging cutting-edge technologies for test automation within the UiPath platform. Attendees will delve into the integration of generative AI, a test automation solution, with Open AI advanced natural language processing capabilities.
Throughout the session, participants will discover how this synergy empowers testers to automate repetitive tasks, enhance testing accuracy, and expedite the software testing life cycle. Topics covered include the seamless integration process, practical use cases, and the benefits of harnessing AI-driven automation for UiPath testing initiatives. By attending this webinar, testers, and automation professionals can gain valuable insights into harnessing the power of AI to optimize their test automation workflows within the UiPath ecosystem, ultimately driving efficiency and quality in software development processes.
What will you get from this session?
1. Insights into integrating generative AI.
2. Understanding how this integration enhances test automation within the UiPath platform
3. Practical demonstrations
4. Exploration of real-world use cases illustrating the benefits of AI-driven test automation for UiPath
Topics covered:
What is generative AI
Test Automation with generative AI and Open AI.
UiPath integration with generative AI
Speaker:
Deepak Rai, Automation Practice Lead, Boundaryless Group and UiPath MVP
Building Production Ready Search Pipelines with Spark and MilvusZilliz
Spark is the widely used ETL tool for processing, indexing and ingesting data to serving stack for search. Milvus is the production-ready open-source vector database. In this talk we will show how to use Spark to process unstructured data to extract vector representations, and push the vectors to Milvus vector database for search serving.
TrustArc Webinar - 2024 Global Privacy SurveyTrustArc
How does your privacy program stack up against your peers? What challenges are privacy teams tackling and prioritizing in 2024?
In the fifth annual Global Privacy Benchmarks Survey, we asked over 1,800 global privacy professionals and business executives to share their perspectives on the current state of privacy inside and outside of their organizations. This year’s report focused on emerging areas of importance for privacy and compliance professionals, including considerations and implications of Artificial Intelligence (AI) technologies, building brand trust, and different approaches for achieving higher privacy competence scores.
See how organizational priorities and strategic approaches to data security and privacy are evolving around the globe.
This webinar will review:
- The top 10 privacy insights from the fifth annual Global Privacy Benchmarks Survey
- The top challenges for privacy leaders, practitioners, and organizations in 2024
- Key themes to consider in developing and maintaining your privacy program
Climate Impact of Software Testing at Nordic Testing DaysKari Kakkonen
My slides at Nordic Testing Days 6.6.2024
Climate impact / sustainability of software testing discussed on the talk. ICT and testing must carry their part of global responsibility to help with the climat warming. We can minimize the carbon footprint but we can also have a carbon handprint, a positive impact on the climate. Quality characteristics can be added with sustainability, and then measured continuously. Test environments can be used less, and in smaller scale and on demand. Test techniques can be used in optimizing or minimizing number of tests. Test automation can be used to speed up testing.
Unlocking Productivity: Leveraging the Potential of Copilot in Microsoft 365, a presentation by Christoforos Vlachos, Senior Solutions Manager – Modern Workplace, Uni Systems
Full-RAG: A modern architecture for hyper-personalizationZilliz
Mike Del Balso, CEO & Co-Founder at Tecton, presents "Full RAG," a novel approach to AI recommendation systems, aiming to push beyond the limitations of traditional models through a deep integration of contextual insights and real-time data, leveraging the Retrieval-Augmented Generation architecture. This talk will outline Full RAG's potential to significantly enhance personalization, address engineering challenges such as data management and model training, and introduce data enrichment with reranking as a key solution. Attendees will gain crucial insights into the importance of hyperpersonalization in AI, the capabilities of Full RAG for advanced personalization, and strategies for managing complex data integrations for deploying cutting-edge AI solutions.
“An Outlook of the Ongoing and Future Relationship between Blockchain Technologies and Process-aware Information Systems.” Invited talk at the joint workshop on Blockchain for Information Systems (BC4IS) and Blockchain for Trusted Data Sharing (B4TDS), co-located with with the 36th International Conference on Advanced Information Systems Engineering (CAiSE), 3 June 2024, Limassol, Cyprus.
GraphSummit Singapore | The Art of the Possible with Graph - Q2 2024Neo4j
Neha Bajwa, Vice President of Product Marketing, Neo4j
Join us as we explore breakthrough innovations enabled by interconnected data and AI. Discover firsthand how organizations use relationships in data to uncover contextual insights and solve our most pressing challenges – from optimizing supply chains, detecting fraud, and improving customer experiences to accelerating drug discoveries.
5. Plan
● Different options to deploy a model (Lambda, Kubernetes, SageMaker)
● Kubernetes 101
● Deploying an XGB model with Flask and Kubernetes
● Deploying a Keras model with TF-Serving and Kubernetes
● Deploying a Keras model with KServe (previously known as Kubeflow
Serving)
6. Ways to deploy a model
● Flask + AWS Elastic Beanstalk
● Serverless (AWS Lambda)
● Kubernetes (EKS)
● KServe (EKS)
● AWS SageMaker
● ...
(or their alternatives in other cloud providers)
12. Lambda vs SageMaker vs Kubernetes
● Lambda
○ Cheap for small load
○ Easy to manage
○ Not always transparent
13. Lambda vs SageMaker vs Kubernetes
● Lambda
○ Cheap for small load
○ Easy to manage
○ Not always transparent
● SageMaker (serving)
○ Easy to use/manage
○ Needs wrappers
○ Not always transparent
○ Expensive
14. Lambda vs SageMaker vs Kubernetes
● Lambda
○ Cheap for small load
○ Easy to manage
○ Not always transparent
● SageMaker (serving)
○ Easy to use/manage
○ Needs wrappers
○ Not always transparent
○ Expensive
● Kubernetes
○ Complex (for me)
○ More flexible
○ Cloud-agnostic *
○ Requires support
○ Cheaper for high load
* sort of
16. Kubernetes glossary
● Pod ~ one instance of your service
● Deployment - a bunch of pods
● HPA - horizontal pod autoscaler
● Node - a server (e.g. EC2 instance)
● Service - an interface to the deployment
● Ingress - an interface to the cluster
20. import xgboost as xgb
# load the model from the pickle file
@app.route('/predict', methods=['POST'])
def predict():
data = request.get_json()
result = apply_model(data)
return jsonify(result)
if __name__ == "__main__":
app.run(debug=True, host='0.0.0.0', port=9696)
21. FROM python:3.9-slim
RUN pip install flask gunicorn xgboost
COPY "model.py" "model.py"
EXPOSE 9696
ENTRYPOINT ["gunicorn", "--bind", "0.0.0.0:9696", "model:app"]
28. import tensorflow as tf
from tensorflow import keras
model = keras.models.load_model('keras-model.h5')
tf.saved_model.save(model, 'tf-model')
29. $ ls -lhR
.:
total 3,1M
4,0K assets
3,1M saved_model.pb
4,0K variables
./assets:
total 0
./variables:
total 83M
83M variables.data-00000-of-00001
15K variables.index
30. saved_model_cli show --dir tf-model --all
MetaGraphDef with tag-set: 'serve' contains the following SignatureDefs:
...
signature_def['serving_default']:
The given SavedModel SignatureDef contains the following input(s):
inputs['input_8'] tensor_info:
dtype: DT_FLOAT
shape: (-1, 299, 299, 3)
name: serving_default_input_8:0
The given SavedModel SignatureDef contains the following output(s):
outputs['dense_7'] tensor_info:
dtype: DT_FLOAT
shape: (-1, 10)
name: StatefulPartitionedCall:0
Method name is: tensorflow/serving/predict
31. docker run -it --rm
-p 8500:8500
-v "$(pwd)/tf-model:/models/tf-model/1"
-e MODEL_NAME=tf-model
tensorflow/serving:2.3.0
2021-09-07 21:03:58.579046: I tensorflow_serving/model_servers/server.cc:367]
Running gRPC ModelServer at 0.0.0.0:8500 ...
[evhttp_server.cc : 238] NET_LOG: Entering the event loop ...
2021-09-07 21:03:58.582097: I tensorflow_serving/model_servers/server.cc:387]
Exporting HTTP/REST API at:localhost:8501 ...
35. Not so fast
def np_to_protobuf(data):
return tf.make_tensor_proto(data, shape=data.shape)
pb_request = predict_pb2.PredictRequest()
pb_request.model_spec.name = 'tf-model'
pb_request.model_spec.signature_name = 'serving_default'
pb_request.inputs['input_8'].CopyFrom(np_to_protobuf(X))
pb_result = stub.Predict(pb_request, timeout=20.0)
pred = pb_result.outputs['dense_7'].float_val
36. 2,0 GB dependency?
Get only the things you need!
https://github.com/alexeygrigorev/tensorflow-protobuf
37. from tensorflow.keras.applications.xception import preprocess_input
https://github.com/alexeygrigorev/keras-image-helper
from keras_image_helper import create_preprocessor
preprocessor = create_preprocessor('xception', target_size=(299, 299))
url = 'http://bit.ly/mlbookcamp-pants'
X = preprocessor.from_url(url)
38. Next steps...
● Bake in the model into the TF-serving image
● Wrap the gRPC calls in a Flask app for the Gateway
● Write a Dockerfile for the Gateway
● Publish the images to ERC
61. Summary
● AWS SageMaker vs AWS Lambda vs Kubernetes vs Kubeflow
● Deploying models with Kubernetes: deployment + service
62. Summary
● AWS SageMaker vs AWS Lambda vs Kubernetes vs Kubeflow
● Deploying models with Kubernetes: deployment + service
● Deploying Keras models: TF-Serving + Gateway (over gRPC)
63. Summary
● AWS SageMaker vs AWS Lambda vs Kubernetes vs Kubeflow
● Deploying models with Kubernetes: deployment + service
● Deploying Keras models: TF-Serving + Gateway (over gRPC)
● KFServing: transformers + model
64. Summary
● AWS SageMaker vs AWS Lambda vs Kubernetes vs Kubeflow
● Deploying models with Kubernetes: deployment + service
● Deploying Keras models: TF-Serving + Gateway (over gRPC)
● KFServing: transformers + model
● No size fits all