# kserve/kserve

Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes

Repository: https://github.com/kserve/kserve
Canonical: https://ross.abutalabs.com/products/kserve
Homepage: https://kserve.github.io/website/
Language: Go
License: Apache-2.0
License Family: permissive
Topics: knative, machine-learning, model-interpretability, model-serving, istio, kubeflow, artificial-intelligence, tensorflow, pytorch, xgboost, kubernetes, k8s, service-mesh, kserve, hacktoberfest, mlops, genai, llm-inference, cncf, vllm
Last push: 2026-08-26T22:20:58+00:00

## Health v2 (maintenance only)
Score: 94/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 84, longevity 100
- inputs: {"age_days": 2716, "days_push": 7, "days_rel": 27, "gap_med": 45, "n_releases_24m": 12}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5834, forks 1636 (observed 2026-08-28T04:09:30.178111+00:00)

## What it is
KServe is a CNCF incubating, Kubernetes-native platform for serving both generative and predictive AI models at scale. It provides a standardized CRD-based API that encapsulates autoscaling, networking, health checking, and multi-framework model serving (TensorFlow, PyTorch, scikit-learn, XGBoost, ONNX, vLLM, Hugging Face).

## Use cases
- serve llms on kubernetes with vllm
- deploy a pytorch model as a rest api on k8s
- openai-compatible inference endpoint for self-hosted models
- scale model serving to zero when idle
- canary rollout of a new model version
- add explainability and drift detection to model predictions
- serve sklearn and xgboost models behind one platform

## When to choose
- you already run Kubernetes and need standardized multi-framework model serving
- you need both LLM (generative) and traditional (predictive) inference on one platform
- you want autoscaling, scale-to-zero, canary rollouts, and traffic management out of the box
- you need GPU-accelerated LLM serving with OpenAI-compatible APIs

## When to avoid
- you deploy models outside Kubernetes or on a single server
- you need only a lightweight standalone inference server without cluster orchestration
- your team cannot operate Kubernetes operators, Istio, and Knative dependencies

## Facets
- artifact type: service
- maturity: stable
- function: machine-learning, llm-inference, api-framework, monitoring, deployment, container-orchestration
- domain: machine-learning, large-language-models, artificial-intelligence, cloud-computing
- platform: go, cloud, self-hosted
- tags: model-serving, inference, kubernetes-operator, vllm, knative, istio, kubeflow, cncf, autoscaling, gpu, openai-compatible, canary-rollouts, model-explainability, devops, mlops, kubernetes, docker

## Member repositories
- kserve/kserve (main) score 94

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:30.178111+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:52:03.988935+00:00, confidence not recorded.
  - readme: https://github.com/kserve/kserve (fetched 2026-08-28T04:09:30.178111+00:00, sha 8e598ee9bd8d)
  - homepage: https://kserve.github.io/website/ (fetched 2026-08-29T08:47:27.020346+00:00, sha 9f28409a28d8)
- Data as of 2026-08-30T08:39:29.467469+00:00.