triton-ascend-migration

Community

Seamlessly migrate GPU Triton kernels to Ascend NPU.

Authordongg622
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill streamlines the process of converting GPU-based Triton kernels into optimized Ascend NPU implementations, reducing manual rewriting effort.

Core Features & Use Cases

  • Automated Code Transformation: Converts CUDA Triton kernels into Ascend-compatible representations, adjusting grid and parallelism models.
  • Optimization Guidance: Suggests improvements for handling coreDim and UB overflow, layout reorganization, and parallel execution strategies.
  • Use Case: Efficiently port machine learning kernels from GPU to Ascend, ensuring performance and correctness while minimizing manual intervention.

Quick Start

Use the triton-ascend-migration skill to transform a GPU Triton kernel located in 'kernel.py' into an Ascend-compatible version and generate a validation script.

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 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: triton-ascend-migration
Download link: https://github.com/dongg622/china-ai-chip-skill/archive/main.zip#triton-ascend-migration

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.