Google Git
Sign in
apache / tvm-vta / 4e035bef0dad34723e0df1f5e416f9910ca8b245
commit4e035bef0dad34723e0df1f5e416f9910ca8b245[log] [tgz]
authorTianqi Chen <tqchen@users.noreply.github.com>Sat Jun 23 21:51:32 2018 -0700
committerTianqi Chen <tqchen@users.noreply.github.com>Wed Jul 11 21:54:39 2018 -0700
treeb949d28170960a1135adb08ca56df0d4840258e1
parent4f79ec9c42f52e80b84b55839a2a1171a2db5780 [diff]
[DOCKER] Cleanup docker image (#50)
5 files changed
tree: b949d28170960a1135adb08ca56df0d4840258e1
  1. apps/
  2. docs/
  3. examples/
  4. hardware/
  5. include/
  6. make/
  7. python/
  8. src/
  9. tests/
  10. tutorials/
  11. CONTRIBUTORS.md
  12. Jenkinsfile
  13. LICENSE
  14. Makefile
  15. NEWS.md
  16. README.md
README.md

VTA: Open, Modular, Deep Learning Accelerator Stack

Build Status GitHub license

VTA(versatile tensor accelerator) is an open-source deep learning accelerator stack. It is not just an open-source hardware, but is an end to end solution that includes the entire software stack on top of VTA open-source hardware.

The key features include:

  • Generic, modular open-source hardware
    • Streamlined workflow to deploy to FPGAs.
    • Simulator support to protoype compilation passes on regular workstations.
  • Driver and JIT runtime for both simulated and FPGA hardware backend.
  • End to end TVM stack integration
    • Direct optimization and deploy models from deep learning frameworks via TVM stack.
    • Customized and extendible TVM compiler backend.
    • Flexible RPC support to ease the deployment, and program FPGAs with Python

VTA is part of our effort on TVM Stack.

VTA Installation

To get started with VTA, please follow the Installation Guide

ResNet-18 Inference Example

To offload ResNet-18 inference, follow the ResNet-18 Guide

License

© Contributors, 2018. Licensed under an Apache-2.0 license.