KServe provides a Kubernetes custom resource definition that handles autoscaling, networking, health checks, and server configuration for model deployments. · kserve.github.io, 5 Oct 2026
Frameworks
Documented serving runtimes include TensorFlow Serving, Triton, Hugging Face, LightGBM, XGBoost, AutoGluon, PMML, scikit-learn, and PaddlePaddle. · kserve.github.io, 5 Oct 2026
Installation
KServe documents installation with Kustomize components or Helm charts and supports multiple deployment modes. · kserve.github.io, 5 Oct 2026
Install options
KServe can be installed with Kustomize components or Helm charts, and can serve predictive models alone or alongside separate LLM and model-caching components. · kserve.github.io, 5 Oct 2026
Integrations
Documented integrations include Istio, Knative Serving, Envoy Gateway, Envoy AI Gateway, and the vLLM runtime. · kserve.github.io, 5 Oct 2026
Known limitation
The optional LocalModel component currently supports InferenceService workloads; support for LLMInferenceService is planned for future releases. · kserve.github.io, 5 Oct 2026
LLM API
The Hugging Face runtime uses vLLM and provides OpenAI-compatible API endpoints for generative tasks including text generation, embeddings, and reranking. · kserve.github.io, 5 Oct 2026
LLM features
Its generative AI features include vLLM and llm-d backends, OpenAI protocol compatibility, GPU acceleration, model caching, KV cache offloading, and request-based autoscaling. · kserve.github.io, 5 Oct 2026
Predictive AI features
It supports TensorFlow, PyTorch, scikit-learn, XGBoost, and ONNX, with routing, InferenceGraph deployments, explainability, monitoring, and scale-to-zero. · kserve.github.io, 5 Oct 2026
Predictive model features
Predictive serving supports canary rollouts, inference pipelines and ensembles, scale-to-zero, explainability, and monitoring features such as payload logging and drift detection. · kserve.github.io, 5 Oct 2026
Project affiliation
The site says KServe has joined CNCF and identifies it as a Series of LF Projects, LLC project. · kserve.github.io, 5 Oct 2026
Protocols
KServe documents gRPC support for its V1 and V2 inference protocols, including binary tensor data and streaming responses. · kserve.github.io, 5 Oct 2026
Purpose
KServe is a Kubernetes platform for serving generative and predictive AI models across multiple frameworks. · kserve.github.io, 5 Oct 2026
Requirements and limits
KServe runs on Kubernetes; its optional LocalModel component currently supports InferenceService workloads, while support for LLMInferenceService is described as planned for a future release. · kserve.github.io, 5 Oct 2026
Rollouts
KServe supports canary rollouts and A/B testing. · kserve.github.io, 5 Oct 2026
Security
The Istio integration documents mutual TLS, automatic certificate management, and fine-grained access-control and authorization policies. · kserve.github.io, 5 Oct 2026
Standard API
It provides a Kubernetes Custom Resource Definition that abstracts autoscaling, networking, health checks, and server configuration. · kserve.github.io, 5 Oct 2026
Support
Users can get help through the documentation, the #kserve Slack channel, GitHub Discussions, and community meetings. · kserve.github.io, 5 Oct 2026
What it does
KServe is an open-source platform for serving generative and predictive AI models on Kubernetes. · kserve.github.io, 5 Oct 2026
Who it is for
The administrator guide covers production management of both predictive and generative inference workloads on Kubernetes. · kserve.github.io, 5 Oct 2026
