Skip to content

// Production LLM inference on Kubernetes with vLLM + KServe — InferenceService, GPU scheduling, scale-to-zero, canary.

KServe vLLM ServingVerified Creator

git log --oneline --stat
HEAD
Stars
5.4k
Forks
316
Updated
Jun 24, 2026
repo --stat

  • stars

    5.4k

  • forks

    316

  • last update

    Jun 24, 2026

  • license

    MITv1.3.0

quickstart.sh
3 steps
  1. Install

    // Drops SKILL.md into ~/.claude/skills/

    $ claude skills add kserve-vllm-llm-serving
  2. Invoke

    // Run from any project directory

    $ claude --skill kserve-vllm-llm-serving "wire up a GitHub Actions deploy"
  3. Iterate

    // Re-run with edits — Claude keeps the skill loaded

    $ claude --skill kserve-vllm-llm-serving "now refactor it"
kserve-vllm-llm-serving/
references
SKILL.md
readonly
name:
KServe vLLM Serving
slug:
kserve-vllm-llm-serving
version:
v1.3.0
license:
MIT
author:
@kserve-craft
repository:
github.com/kserve-craft/kserve-vllm-llm-serving
categories:
DevOps / CI/CDML / AI
tags:
#kserve#vllm#kubernetes#llm-inference#scale-to-zero
description:

Production LLM inference on Kubernetes with vLLM + KServe — InferenceService, GPU scheduling, scale-to-zero, canary.

features.md
3 capabilities

// What you can do with it

  • Automates the tedious parts of the workflow.
  • Gives Claude the right context, tools, and guardrails.
  • Produces consistent, reviewable output every time.

README.md

kserve-vllm-llm-serving/README.md
5 sections
Loading README…

$ cat reviews/

Reviews

// No reviews yet. Be the first.
Loading review form…

$ ls related/

explore all →