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.

LLM inference optimization with TensorRT-LLM v1.0.0

Use this resource to optimize and serve an LLM on NVIDIA GPUs with TensorRT-LLM

New

  • 386 downloads
  • 153 likes
  • 148 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install tensorrt-llm-inference-optimization

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 walks you through installing TensorRT-LLM, basic inference, quantization (FP8, INT4) and serving with trtllm-serve. You get a deployment configuration and the points to watch.

Mostly picked by

Updated November 2, 2026

Card for the “LLM inference optimization with TensorRT-LLM” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: when to use TensorRT-LLM, installation and basic inference
  • references/serving.md: serving with trtllm-serve
  • references/optimization.md and references/multi-gpu.md: tuning and scaling

Good fit for

  • You deploy a model to production on NVIDIA A100 or H100 GPUs
  • You need more throughput or lower latency than PyTorch alone gives

Not for

    Tags

    • tensorrt-llm
    • inference
    • quantization
    • nvidia gpu

    About

    You say

    “Prepare a TensorRT-LLM deployment of an 8B model in FP8, served on two H100 GPUs.”

    Card for the “LLM inference optimization with TensorRT-LLM” 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 optimize and serve an LLM on NVIDIA GPUs with TensorRT-LLM
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/multi-gpu.md6.8 KB
    • references/optimization.md5.7 KB
    • references/serving.md10 KB
    • SKILL.md5.1 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-tensorrt-llm
    Licence
    MIT

    Notice

    « inference-serving-tensorrt-llm » (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.