Google Git
Sign in
apache / tvm-vta / f187a39f273961b1c2acc52088cc0a2305e5b247
commitf187a39f273961b1c2acc52088cc0a2305e5b247[log] [tgz]
authorHua Jiang <huaj@xilinx.com>Thu Mar 11 06:41:04 2021 -0800
committerGitHub <noreply@github.com>Thu Mar 11 09:41:04 2021 -0500
treee7b3d792cd34ff2ae261fe4ea403cf245ac85578
parent5bd9c6a8b487234e18069c887b3f6271c97292f7 [diff]
Make VTA C++ Deploy Compatible with latest TVM. (#22)

Issue:
c++ deployment get broken after recently TVM change,
first issue is lastest TVM use some c++14 feature in
header file that caused current compile fail.

second issue is lastest TVM did more strict format/type
check that make the restnet export logic failed.

Solution:
Fix the said issue to make logic work.
2 files changed
tree: e7b3d792cd34ff2ae261fe4ea403cf245ac85578
  1. apps/
  2. config/
  3. hardware/
  4. include/
  5. src/
  6. tests/
  7. .asf.yaml
  8. .gitignore
  9. Jenkinsfile
  10. LICENSE
  11. NOTICE
  12. README.md
README.md

VTA Hardware Design Stack

Build Status

VTA (versatile tensor accelerator) is an open-source deep learning accelerator complemented with an end-to-end TVM-based compiler stack.

The key features of VTA include:

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