KServe is a Kubernetes-native platform for deploying and serving machine learning models as scalable inference services. It supports both generative AI models, including large language models, and traditional predictive models from frameworks such as TensorFlow, PyTorch, Scikit-Learn, XGBoost, and ONNX. The platform manages the full lifecycle of model deployments, including revision tracking, canary rollouts, A/B testing, and automatic rollbacks, and provides serverless scale-to-zero capabilities for cost-efficient resource management. KServe distinguishes itself through a standardized infere
Space Cloud is a self-hosted, cloud-native backend-as-a-service suite. It functions as a Kubernetes-based serverless platform that provides a GraphQL and REST API gateway, a database API generator, and an event-driven orchestrator. The platform transforms SQL and NoSQL database schemas into secure endpoints, eliminating the need for manual backend development. It distinguishes itself by allowing remote data joins, which combine records from internal databases and external HTTP microservices within a single query. The system covers a broad range of capabilities, including rule-based access co
Nuclio is a high-performance serverless framework designed for Kubernetes that automatically executes user functions when events arrive from HTTP endpoints, message queues, or streaming data platforms. It processes hundreds of thousands of events per second per function instance through efficient parallel workers, and can allocate functions to run on either CPU or GPU hardware to match workload requirements for data processing or machine learning tasks. The platform scales function instances down to zero when idle and wakes them on demand based on incoming event load, while providing an event
Kubeless is a Kubernetes-native serverless framework that deploys and runs stateless functions as custom resources managed by an in-cluster controller. It functions as a Function-as-a-Service platform, launching function runtime pods on demand and scaling them to zero when idle to optimise resource usage. Functions are invoked automatically through HTTP requests or a publish-subscribe messaging bus, enabling event-driven execution for workloads and microservices. The platform supports running functions written in Golang, Python, Node.js, Ruby, PHP, .NET, and Ballerina, with the ability to add
Kubernetes-based, scale-to-zero, request-driven compute
knative/serving 的主要功能包括:Kubernetes-Native, CloudEvent-Triggered Invocations, Immutable Revision Snapshots, Zero-Instance Scaling, Immutable Revision Configurations, Kubernetes Ecosystem, Serverless Function Invokers, Native Kubernetes Resource Integration。
knative/serving 的开源替代品包括: kserve/kserve — KServe is a Kubernetes-native platform for deploying and serving machine learning models as scalable inference… spacecloud-io/space-cloud — Space Cloud is a self-hosted, cloud-native backend-as-a-service suite. It functions as a Kubernetes-based serverless… nuclio/nuclio — Nuclio is a high-performance serverless framework designed for Kubernetes that automatically executes user functions… vmware-archive/kubeless — Kubeless is a Kubernetes-native serverless framework that deploys and runs stateless functions as custom resources… serverless/event-gateway — The Event Gateway is a unified routing layer designed to connect HTTP requests and cloud events to serverless… kubeflow/kfserving — KServe is an open platform for deploying and serving generative and predictive AI models on Kubernetes. It defines…