skills.rest
NVIDIA
NVIDIAOFFICIAL
Explore all skills by this author →
WebsiteGitHub

exec-local-compile

Build and install TensorRT-LLM from source in a Docker container with visible GPUs.

2.8k|332|Updated Feb 25, 2026
Search Tags:#build#docker#gpu#installation#compile#tensorrt-llm
One-click install
npx skills add https://github.com/NVIDIA/skills --skill exec-local-compile
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: exec-local-compile
Source: https://github.com/NVIDIA/skills/tree/main/skills/TensorRT-LLM/exec-local-compile
Command: npx skills add https://github.com/NVIDIA/skills --skill exec-local-compile

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Compile TensorRT-LLM from source on a compute node inside a Docker container when GPUs are visible, enabling optimized deployment.

Core Features & Use Cases

  • Local GPU-accelerated build: Build TensorRT-LLM from source on a compute node with visible GPUs inside a container.
  • Containerized workflow: Uses Docker/enroot to provide a reproducible build environment.
  • Use Case: Developers can produce a wheel and install TensorRT-LLM for testing on the target GPU hardware.

Quick Start

Run the build and install steps to compile TensorRT-LLM on a Docker container with GPUs visible.

Frequently Asked Questions about exec-local-compile

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I compile TensorRT-LLM from source on a GPU compute node?▼

To compile TensorRT-LLM from source, run the build and install steps inside a Docker container on a GPU compute node with visible GPUs. This builds the project against TensorRT and installs the Python package in editable mode.

Why does my TensorRT-LLM build fail on a SLURM login node?▼

A TensorRT-LLM build fails on a SLURM login node because GPUs are not visible there. You must execute the build process on a GPU compute node or inside a container that has direct access to GPU hardware.

Can I use Docker to build TensorRT-LLM in a reproducible environment?▼

Yes, you can use Docker to build TensorRT-LLM in a reproducible environment. The containerized workflow ensures consistent dependencies while compiling the project directly on your target GPU hardware.

Do I need visible GPUs to install TensorRT-LLM in editable mode?▼

Yes, visible GPUs are required to install TensorRT-LLM in editable mode. The build process enforces environment checks to ensure it operates on a GPU compute node rather than a login node.

What's the best way to build a TensorRT-LLM wheel for testing on target hardware?▼

The best way to build a TensorRT-LLM wheel for testing is to compile it from source inside a Docker container on a GPU-enabled compute node. This produces an optimized wheel for your specific hardware.

Related Skills

Explore More Software Engineering Skills→
NVIDIA-TAONVIDIA-TAO
83

tao-run-on-slurm

Automate remote TAO GPU job submission on SLURM clusters via SSH.

Official
Advanced
aayushsoamaayushsoam
1

tensorrt-llm

Optimize LLM inference on NVIDIA GPUs with TensorRT.

Community
Advanced
GitnappGitnapp

modal-serverless-gpu

Deploy and manage machine learning workloads on Modal serverless GPU infrastructure.

Community
Advanced
ovachieverovachiever
52

tensorrt-llm

Optimize LLM inference on NVIDIA GPUs with TensorRT-LLM.

Community
Advanced