Get Started Tutorials

Quick Start Tutorial for Compiling Deep Learning Models

Cross Compilation and RPC

Get Started with Tensor Expression

Compile Deep Learning Models

Compile ONNX Models

Deploy Single Shot Multibox Detector(SSD) model

Using External Libraries in Relay

Compile CoreML Models

Compile Keras Models

Deploy a Quantized Model on Cuda

Compile Caffe2 Models

Compile MXNet Models

Compile PyTorch Models

Deploy the Pretrained Model on Raspberry Pi

Deploy a Framework-prequantized Model with TVM

Compile TFLite Models

Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)

Deploy the Pretrained Model on Android

Compile Tensorflow Models

Compile YOLO-V2 and YOLO-V3 in DarkNet Models

Building a Graph Convolutional Network

Deploy a Hugging Face Pruned Model on CPU

Tensor Expression and Schedules

Use Tensor Expression Debug Display (TEDD) for Visualization

External Tensor Functions

Compute and Reduce with Tuple Inputs

Reduction

Scan and Recurrent Kernel

Intrinsics and Math Functions

Schedule Primitives in TVM

Use Tensorize to Leverage Hardware Intrinsics

Optimize Tensor Operators

How to optimize convolution on GPU

How to optimize GEMM on CPU

How to optimize convolution using TensorCores

How to optimize matmul with Auto TensorCore CodeGen

Auto tuning

Writing tunable template and Using auto-tuner

Tuning High Performance Convolution on NVIDIA GPUs

Auto-tuning a convolutional network for NVIDIA GPU

Auto-tuning a convolutional network for x86 CPU

Auto-tuning a convolutional network for ARM CPU

Auto-tuning a convolutional network for Mobile GPU

Developer Tutorials

Writing a Customized Pass

How to Use Relay Pass Infra

TOPI: TVM Operator Inventory

Introduction to TOPI

Micro TVM

Micro TVM with TFLite Models