Skip to main content
🎉️
KServe has joined CNCF!
🥳️
KServe
Getting Started
Quickstart Guide
Tutorials
Serve an LLM
Serve an LLM (Advanced)
Serve a Predictive Model
Swagger UI
Docs
Overview
Concepts
Architecture Overview
Control Plane
Data Plane
Resources
Model Serving
Generative AI Serving
Predictive AI Serving
Inference Graph
Model Storage
Install & Ops
Installation
Admin Guide
Developer Guide
Reference
API Reference
Integrations
Community
Get Involved
Adopters
Presentations
Blog
0.17
nightly
0.17
0.16
0.15
0.14
0.13
0.12
0.11
Archive
Archive
2026
March 5 - Best of Both Worlds: Cloud-Native AI Inference at Scale using KServe and llm-d
March 13 - Announcing KServe v0.17 - Production-Ready LLM Serving with LLMInferenceService
April 21 - Production-Grade LLM Inference at Scale with KServe, llm-d, and vLLM
2025
May 27 - Announcing KServe v0.15 - Advancing Generative AI Model Serving
2024
May 15 - From Serverless Predictive Inference to Generative Inference - Introducing KServe v0.13
December 13 - Announcing KServe v0.14
2023
February 5 - Announcing KServe v0.10.0
October 8 - Announcing KServe v0.11
2022
February 18 - Announcing KServe v0.8
July 21 - Announcing KServe v0.9.0
2021
September 27 - KServe: The next generation of KFServing
October 11 - Announcing KServe v0.7 - Smooth Transition from KFServing to KServe