Search Results for "half-edge"

...It aims to solve production model serving use cases by providing performant, high abstraction interfaces for common ML frameworks like Tensorflow, XGBoost, ScikitLearn, PyTorch, and ONNX. It encapsulates the complexity of autoscaling, networking, health checking, and server configuration to bring cutting edge serving features like GPU Autoscaling, Scale to Zero, and Canary Rollouts to your ML deployments. It enables a simple, pluggable, and complete story for Production ML Serving including prediction, pre-processing, post-processing and explainability. KServe is being used across various organizations.

...Nebula container orchestrator aims to help devs and ops treat IoT devices just like distributed Dockerized apps. It aim is to act as Docker orchestrator for IoT devices as well as for distributed services such as CDN or edge computing that can span thousands (possibly even millions) of devices worldwide and it does it all while being open-source and completely free. Nebula imposes no limits on the scale of the cluster, each component in it is designed to scale out to allow millions of workers to be managed by it. Designed to connect to devices that are spread around the globe Nebula is tolerant of network connection issues and will resync the device when it reconnects. ...

Nebula is a open source distributed Docker orchestrator designed for massive scales (tens of thousands of servers/worker devices), unlike Mesos/Swarm/Kubernetes it has the ability to have workers distributed on high latency connections (such as the internet) yet have the pods(containers) be managed centrally with changes taking affect (almost) immediately, this makes Nebula ideal for managing a vast cluster of servers\devices across the globe, some example use cases are appliances\virtual appliances located at clients data centers, edge computing, and POS systems. Ever wandered how your going to push an update to that smart fridge your company is working on as it's thousands of devices around the globe? wish you could have the assurance that your service will always use the latest code\envvars\etc in all of it's edge locations? want the ability to stop\start a globally distributed service with a single command? ...

...Ever wandered how your going to push an update to that smart fridge your company is working on as it's thousands of devices around the globe? wish you could have the assurance that your service will always use the latest code\envvars\etc in all of its edge locations? want the ability to stop\start a globally distributed service with a single command? Nebula was designed from the ground up to answer all of these needs and much more, refer to the documentation if your interested in seeing how to use it.

Nebula is a open source distributed Docker orchestrator designed for massive scales (tens of thousands of servers/worker devices), unlike Mesos/Swarm/Kubernetes it has the ability to have workers distributed on high latency connections (such as the internet) yet have the pods(containers) be managed centrally with changes taking affect (almost) immediately, this makes Nebula ideal for managing a vast cluster of servers\devices across the globe, some example use cases are IoT devices, appliances\virtual appliances located at clients data centers, and edge computing. Nebula imposes no limits on the scale of the cluster, each component in it is designed to scale out to allow millions of workers to be managed by it. Designed to connect to devices that are spread around the globe Nebula is tolerant of network connection issues and will resync the device when it reconnects. With a single API call you can deploy a new container version to managed devices around the globe in minutes.