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
OpenLLM is a framework for deploying, managing, and scaling open-source large language models
Autoscale LLM (vLLM, SGLang, LMDeploy) inferences on Kubernetes (and others)
The main features of tensorchord/openmodelz are: MLOps Platforms.
Open-source alternatives to tensorchord/openmodelz include: bentoml/openllm — OpenLLM is a framework for deploying, managing, and scaling open-source large language models. dstack-tee/dstack — Open framework for confidential AI. infuseai/primehub — open-source MLOps platform. kserve/kserve — KServe is a Kubernetes-native platform for deploying and serving machine learning models as scalable inference… kubeflow/kubeflow — Kubeflow is a Kubernetes machine learning platform and containerized toolkit designed to orchestrate the entire… logicalclocks/hopsworks — Hopsworks - Data-Intensive AI platform with a Feature Store.
