trtllm-codebase-exploration

Official

Navigate TRT-LLM codebases efficiently.

AuthorNVIDIA
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Systematic approach to exploring the TensorRT-LLM codebase before implementing new features or optimizations. Teaches how to discover existing infrastructure, trace code paths, and avoid reimplementing what already exists. Derived from real mistakes where ~250 lines of code were written and deleted because existing forward methods weren't discovered upfront.

Core Features & Use Cases

  • Systematic codebase mapping to locate relevant modules and utilities.
  • Guided tracing of code paths to find reusable components and minimize rework.
  • Real-world lessons distilled from past iterative mistakes to avoid rework.

Quick Start

Begin by mapping the TRT-LLM codebase to identify existing infrastructure before implementing a new feature.

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: trtllm-codebase-exploration
Download link: https://github.com/NVIDIA/skills/archive/main.zip#trtllm-codebase-exploration

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.