exec-local-compile

Official

Compile TensorRT-LLM on a GPU compute node.

AuthorNVIDIA
Version1.0.0
Installs0

System Documentation

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.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: exec-local-compile
Download link: https://github.com/NVIDIA/skills/archive/main.zip#exec-local-compile

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.