README.md 849 Bytes
Newer Older
1 2
VTA: Open, Modular, Deep Learning Accelerator Stack
===================================================
3
VTA (versatile tensor accelerator) is an open-source deep learning accelerator complemented with an end-to-end TVM-based compiler stack.
4

5
The key features of VTA include:
6

7
- Generic, modular, open-source hardware
8
  - Streamlined workflow to deploy to FPGAs.
9 10 11 12 13 14
  - 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.
15

16
Learn more about VTA [here](https://docs.tvm.ai/vta/index.html).