Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Serve an LLM in production with vLLM v1.0.0

Use this resource to deploy an LLM in production behind an OpenAI-compatible API

New

  • 590 downloads
  • 106 likes
  • 156 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install vllm-llm-serving-api

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent configures vLLM to serve a model on one or several GPUs, chooses quantization and parallelism, then checks the API with the OpenAI SDK. It can also prepare a simple load test.

Mostly picked by

Updated November 2, 2026

Card for the “Serve an LLM in production with vLLM” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: quick start, requests with the OpenAI SDK and production deployment
  • references/: optimisation, quantization, server deployment and troubleshooting

Good fit for

  • You want an internal API for an open model with high throughput
  • A 30B to 70B model must run across several GPUs

Not for

    Tags

    • vllm
    • llm
    • inference
    • gpu
    • openai api

    About

    You say

    “Deploy this model quantized to FP8 on two GPUs, behind an OpenAI-compatible API.”

    Card for the “Serve an LLM in production with vLLM” skill

    Skill published by Orchestra Research under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to deploy an LLM in production behind an OpenAI-compatible API
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/optimization.md5.6 KB
    • references/quantization.md6.6 KB
    • references/server-deployment.md5.1 KB
    • references/troubleshooting.md8.8 KB
    • SKILL.md9.1 KB

    Origin and licence

    Listed unmodified

    Author
    Orchestra Research
    Source
    github.com/nousresearch/hermes-agent/tree/0c74cc682dc81bf78b78a1737b3ee77a820ccb79/optional-skills/mlops/inference/serving-llms-vllm
    Licence
    MIT

    Notice

    « serving-llms-vllm » (Orchestra Research, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.