Getting Started With TVM¶

../_images/sphx_glr_introduction_thumb.png — Introduction¶

../_images/sphx_glr_install_thumb.png — Installing TVM¶

../_images/sphx_glr_tvmc_command_line_driver_thumb.png — Compiling and Optimizing a Model with TVMC¶

../_images/sphx_glr_autotvm_relay_x86_thumb.png — Compiling and Optimizing a Model with the Python Interface (AutoTVM)¶

../_images/sphx_glr_tensor_expr_get_started_thumb.png — Working with Operators Using Tensor Expression¶

../_images/sphx_glr_autotvm_matmul_x86_thumb.png — Optimizing Operators with Schedule Templates and AutoTVM¶

../_images/sphx_glr_auto_scheduler_matmul_x86_thumb.png — Optimizing Operators with Auto-scheduling¶

../_images/sphx_glr_cross_compilation_and_rpc_thumb.png — Cross Compilation and RPC¶

../_images/sphx_glr_relay_quick_start_thumb.png — Quick Start Tutorial for Compiling Deep Learning Models¶

Compile Deep Learning Models¶

../_images/sphx_glr_from_pytorch_thumb.png — Compile PyTorch Models¶

../_images/sphx_glr_from_tensorflow_thumb.png — Compile Tensorflow Models¶

../_images/sphx_glr_from_mxnet_thumb.png — Compile MXNet Models¶

../_images/sphx_glr_from_onnx_thumb.png — Compile ONNX Models¶

../_images/sphx_glr_from_keras_thumb.png — Compile Keras Models¶

../_images/sphx_glr_from_tflite_thumb.png — Compile TFLite Models¶

../_images/sphx_glr_from_coreml_thumb.png — Compile CoreML Models¶

../_images/sphx_glr_from_darknet_thumb.png — Compile YOLO-V2 and YOLO-V3 in DarkNet Models¶

../_images/sphx_glr_from_caffe2_thumb.png — Compile Caffe2 Models¶

../_images/sphx_glr_build_gcn_thumb.png — Building a Graph Convolutional Network¶

../_images/sphx_glr_deploy_model_on_android_thumb.png — Deploy the Pretrained Model on Android¶

../_images/sphx_glr_deploy_model_on_rasp_thumb.png — Deploy the Pretrained Model on Raspberry Pi¶

../_images/sphx_glr_deploy_object_detection_pytorch_thumb.png — Compile PyTorch Object Detection Models¶

../_images/sphx_glr_deploy_prequantized_thumb.png — Deploy a Framework-prequantized Model with TVM¶

../_images/sphx_glr_deploy_prequantized_tflite_thumb.png — Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)¶

../_images/sphx_glr_deploy_quantized_thumb.png — Deploy a Quantized Model on Cuda¶

../_images/sphx_glr_deploy_sparse_thumb.png — Deploy a Hugging Face Pruned Model on CPU¶

../_images/sphx_glr_deploy_ssd_gluoncv_thumb.png — Deploy Single Shot Multibox Detector(SSD) model¶

../_images/sphx_glr_using_external_lib_thumb.png — Using External Libraries in Relay¶

Tensor Expression and Schedules¶

../_images/sphx_glr_schedule_primitives_thumb.png — Schedule Primitives in TVM¶

../_images/sphx_glr_reduction_thumb.png — Reduction¶

../_images/sphx_glr_intrin_math_thumb.png — Intrinsics and Math Functions¶

../_images/sphx_glr_scan_thumb.png — Scan and Recurrent Kernel¶

../_images/sphx_glr_extern_op_thumb.png — External Tensor Functions¶

../_images/sphx_glr_tensorize_thumb.png — Use Tensorize to Leverage Hardware Intrinsics¶

../_images/sphx_glr_tuple_inputs_thumb.png — Compute and Reduce with Tuple Inputs¶

../_images/sphx_glr_tedd_thumb.png — Use Tensor Expression Debug Display (TEDD) for Visualization¶

Optimize Tensor Operators¶

../_images/sphx_glr_opt_gemm_thumb.png — How to optimize GEMM on CPU¶

../_images/sphx_glr_opt_conv_cuda_thumb.png — How to optimize convolution on GPU¶

../_images/sphx_glr_opt_conv_tensorcore_thumb.png — How to optimize convolution using TensorCores¶

AutoTVM : Template-based Auto Tuning¶

../_images/sphx_glr_tune_conv2d_cuda_thumb.png — Tuning High Performance Convolution on NVIDIA GPUs¶

../_images/sphx_glr_tune_relay_cuda_thumb.png — Auto-tuning a Convolutional Network for NVIDIA GPU¶

../_images/sphx_glr_tune_relay_x86_thumb.png — Auto-tuning a Convolutional Network for x86 CPU¶

../_images/sphx_glr_tune_relay_arm_thumb.png — Auto-tuning a Convolutional Network for ARM CPU¶

../_images/sphx_glr_tune_relay_mobile_gpu_thumb.png — Auto-tuning a Convolutional Network for Mobile GPU¶

AutoScheduler : Template-free Auto Scheduling¶

../_images/sphx_glr_tune_conv2d_layer_cuda_thumb.png — Auto-scheduling a Convolution Layer for GPU¶

../_images/sphx_glr_tune_network_x86_thumb.png — Auto-scheduling a Neural Network for x86 CPU¶

../_images/sphx_glr_tune_network_cuda_thumb.png — Auto-scheduling a Neural Network for NVIDIA GPU¶

../_images/sphx_glr_tune_network_arm_thumb.png — Auto-scheduling a Neural Network for ARM CPU¶

../_images/sphx_glr_tune_network_mali_thumb.png — Auto-scheduling a Neural Network for mali GPU¶

../_images/sphx_glr_tune_sparse_x86_thumb.png — Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule¶

Developer Tutorials¶

../_images/sphx_glr_low_level_custom_pass_thumb.png — Writing a Customized Pass¶

../_images/sphx_glr_use_pass_infra_thumb.png — How to Use TVM Pass Infra¶

../_images/sphx_glr_bring_your_own_datatypes_thumb.png — Bring Your Own Datatypes to TVM¶

TOPI: TVM Operator Inventory¶

../_images/sphx_glr_intro_topi_thumb.png — Introduction to TOPI¶

microTVM¶

../_images/sphx_glr_micro_reference_vm_thumb.png — microTVM Reference Virtual Machines¶

../_images/sphx_glr_micro_tflite_thumb.png — microTVM with TFLite Models¶

Gallery generated by Sphinx-Gallery