Skip to content
/ tvm Public
forked from apache/tvm

Open deep learning compiler stack for cpu, gpu and specialized accelerators

License

Notifications You must be signed in to change notification settings

neo-ai/tvm

This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.

Folders and files

NameName
Last commit message
Last commit date
Feb 20, 2019
Mar 20, 2019
Mar 29, 2019
Jan 26, 2019
Mar 29, 2019
Mar 12, 2019
Mar 24, 2019
Mar 20, 2019
Feb 20, 2019
Apr 10, 2019
Mar 20, 2019
Mar 19, 2019
Apr 10, 2019
Apr 10, 2019
Mar 24, 2019
Apr 10, 2019
Apr 10, 2019
Apr 10, 2019
Apr 10, 2019
Aug 23, 2018
Mar 12, 2019
Mar 12, 2019
Feb 20, 2019
Feb 20, 2019
Feb 20, 2019
May 23, 2017
Mar 20, 2019
Mar 29, 2019
Mar 29, 2019
May 10, 2017
Feb 20, 2019
Feb 20, 2019
Feb 20, 2019
Apr 1, 2019
Mar 29, 2019
Mar 12, 2019

Repository files navigation

Open Deep Learning Compiler Stack

GitHub license Build Status

Documentation | Contributors | Community | Release Notes

TVM is a compiler stack for deep learning systems. It is designed to close the gap between the productivity-focused deep learning frameworks, and the performance- and efficiency-focused hardware backends. TVM works with deep learning frameworks to provide end to end compilation to different backends. Checkout the tvm stack homepage for more information.

Neo-ai/tvm is a AWS-managed fork of TVM, that hosts vendor- and product-oriented features on top of upstream codebase.

Branches

  • dev Build Status - This is the development branch with most update to date source codes.

License

© Contributors Licensed under an Apache-2.0 license.

Contribute to TVM

TVM adopts apache committer model, we aim to create an open source project that is maintained and owned by the community. Checkout the Contributor Guide

Acknowledgement

We learnt a lot from the following projects when building TVM.

  • Halide: TVM uses HalideIR as data structure for arithmetic simplification and low level lowering. We also learnt and adapted some part of lowering pipeline from Halide.
  • Loopy: use of integer set analysis and its loop transformation primitives.
  • Theano: the design inspiration of symbolic scan operator for recurrence.

About

Open deep learning compiler stack for cpu, gpu and specialized accelerators

Topics

Resources

License

Code of conduct

Security policy

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Python 54.7%
  • C++ 38.9%
  • Rust 1.3%
  • C 1.2%
  • CMake 0.8%
  • Shell 0.8%
  • Other 2.3%