ai4s-profiling

Community

Streamline performance analysis of AI models on Ascend NPUs.

Authordongg622
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill enables detailed profiling and performance analysis of AI workloads on Huawei Ascend NPU hardware, helping engineers identify bottlenecks and optimize training or inference.

Core Features & Use Cases

  • Performance Data Collection: Uses torch_npu's profiler to gather detailed hardware activity metrics during model execution.
  • Analysis & Optimization: Facilitates identification of computation bottlenecks, memory issues, and runtime inefficiencies for better model tuning.
  • Use Case: An engineer running a training job can deploy this Skill to collect profiling data, visualize performance, and optimize the model for hardware efficiency.

Quick Start

Attach the profiling code to your PyTorch training loop to collect performance traces and identify hotspots on Ascend NPU.

Dependency Matrix

Required Modules

torch_npu

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: ai4s-profiling
Download link: https://github.com/dongg622/china-ai-chip-skill/archive/main.zip#ai4s-profiling

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.