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.

High-throughput LLM serving with vLLM v1.0.0

Use this resource to deploy an LLM with vLLM for high throughput and low latency

New

  • 500 downloads
  • 129 likes
  • 220 saves

Free

Install with the CLI

In a terminal, from the folder you want:

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

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 sets up a vLLM server with PagedAttention and continuous batching, fits GPU memory use to the model, applies quantization such as GPTQ, AWQ or FP8, and splits the model across several GPUs. You get an OpenAI-compatible API and load-testing steps.

Mostly picked by

Updated November 2, 2026

Card for the “High-throughput LLM serving 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, deployment workflows and load testing
  • references/quantization.md: quantization formats
  • references/troubleshooting.md: common issues and fixes

Good fit for

  • You expose an open-source model through an OpenAI-compatible API
  • Your GPU does not have enough memory for the model you want

Not for

    Tags

    • vllm
    • inference
    • llm

    About

    You say

    “Deploy Llama 3 8B on my GPU with an OpenAI-compatible API and AWQ quantization.”

    Card for the “High-throughput LLM serving with vLLM” skill

    Skill published by davila7 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 with vLLM for high throughput and low latency
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/optimization.md5.9 KB
    • references/quantization.md6.9 KB
    • references/server-deployment.md5.4 KB
    • references/troubleshooting.md9.3 KB
    • SKILL.md9.2 KB

    Origin and licence

    Listed unmodified

    Author
    davila7
    Source
    github.com/davila7/claude-code-templates/tree/f57964ebda91cdfb31755661ecea9395f30020f1/cli-tool/components/skills/ai-research/inference-serving-vllm
    Licence
    MIT

    Notice

    « inference-serving-vllm » (davila7, 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.