skills.rest
jstzwj
jstzwjCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

tvm

Import models from PyTorch, ONNX, and TFLite into Relax IR for optimization.

4|Updated May 6, 2026
Search Tags:#code generation#model deployment#tvm#ml optimization#schedule tuning#IR transformation
One-click install
npx skills add https://github.com/jstzwj/ai-infra-plugins --skill tvm
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: tvm
Source: https://github.com/jstzwj/ai-infra-plugins/tree/main/plugins/tvm/skills/tvm
Command: npx skills add https://github.com/jstzwj/ai-infra-plugins --skill tvm

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides comprehensive tools for optimizing, compiling, and deploying machine learning models efficiently across diverse hardware platforms.

Core Features & Use Cases

  • Model Import & Conversion: Supports seamless import from frameworks like PyTorch, ONNX, and TFLite into Relax IR for further optimization.
  • IR Optimization & Transformation: Offers a suite of passes to legalize, fuse, and simplify models, preparing them for deployment.
  • Hardware Targeting & Codegen: Enables compilation to various backends including LLVM, CUDA, OpenCL, and others, ensuring optimal performance.
  • Use Case: For example, developers can import a pre-trained image classification model, optimize it with TVM's advanced passes and auto-tune the schedule, then deploy on edge devices or cloud platforms.

Quick Start

Use TVM to import a model, optimize it via relaxation pipelines, compile for the target hardware, and execute inference with minimal setup.

Frequently Asked Questions about tvm

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

FAQPage Schema
How do I compile and deploy machine learning models across different hardware targets?▼

To compile and deploy machine learning models across hardware targets, you can import frameworks like PyTorch or ONNX, optimize via IR passes, and generate code for CPU, GPU, or accelerators. This ensures efficient cross-platform execution.

Can I import PyTorch and ONNX models for hardware-specific code generation?▼

Yes, you can import PyTorch and ONNX models into Relax IR for optimization. The framework then performs hardware-specific code generation for backends like LLVM, CUDA, and OpenCL to enable efficient deployment.

How does IR transformation optimize deep learning models for edge devices?▼

IR transformation optimizes deep learning models by applying passes to legalize, fuse, and simplify computations. This prepares the model for schedule tuning and automatic code generation, ensuring peak performance on edge devices.

What is the best way to auto-tune schedules for ML deployment on specialized accelerators?▼

The best way to auto-tune schedules for ML deployment on specialized accelerators is to import the model, apply IR optimization passes, and use the framework's auto-tuning capabilities to generate highly optimized hardware-specific code.

Does this framework support model conversion from TFLite for edge deployment?▼

Yes, the framework supports seamless model conversion from TFLite into Relax IR. After conversion, you can optimize the model and compile it for efficient deployment across various edge devices and cloud platforms.

Related Skills

Explore More Software Engineering Skills→
Pico-DeveloperPico-Developer
2

spatialml

Convert ONNX, TFLite, PB, and PyTorch models to QNN context binaries.

Official
Advanced
michaelalbermichaelalber
2

edge-cv-pipeline

Build optimized computer vision pipelines for edge devices like Jetson and Raspberry Pi.

Community
Advanced
backengineeringbackengineering
434

llvm-optimization

Analyze LLVM IR and apply optimization passes to improve generated code.

Official
Advanced
NeverSightNeverSight
69

compiler-development

Develop LLVM-based compiler pipelines from frontends to optimized code generation.

Official
Advanced