nnvm.tvmlang.orgTVM Documentation — tvm 0.8.dev0 documentation

Community Download VTA Blog Docs Conference Github ASF Apache Homepage License Sponsorship Security Thanks Events ASF Apache Homepage License Sponsorship Security Thanks Events 0.8.dev0 How to Installation Contribute to TVM Deploy and Integration Developer How-To Guide microTVM: TVM on bare-metal Tutorials Get Started Tutorials Compile Deep Learning Models Tensor Expression and Schedules Optimize Tensor Operators AutoTVM : Template-based Auto Tuning AutoScheduler : Template-free Auto Scheduling Developer Tutorials TOPI: TVM Operator Inventory microTVM References Language Reference Python API Links to Other API References Deep Dive Design and Architecture MISC VTA: Deep Learning Accelerator Stack Frequently Asked Questions Index Table of content Docs > TVM Documentation TVM Documentation ¶ TVM is an open deep learning compiler stack for CPUs, GPUs, and specialized accelerators. It aims to close the gap between the productivity-focused deep learning frameworks, and the performance- or efficiency-oriented hardware backends. Get Started ¶ Follow the instructions to install TVM. Checkout the tutorials . For Developers ¶ Design and Architecture is useful for developers who want to understand the architecture of TVM and/or actively develop on the project. Developer How-To Guide gives quick development tips on various topics. Index ¶ Index Next © 2020 Apache Software Foundation | All right reserved Copyright © 2020 The Apache Software Foundation. Apache TVM, Apache, the Apache feather, and the Apache TVM project logo are either trademarks or registered trademarks of the Apache Software Foundation....