layout: index title: “Apache TVM”

{::options parse_block_html=“true” /}

* Compilation of deep learning models into minimum deployable modules.
* Infrastructure to automatic generate and optimize models on more backend with better performance.
  • {:.key-block} Performance


Compilation and minimal runtimes commonly unlock  ML workloads on existing hardware.
  • {:.key-block} Run Everywhere

Run Everywhere

CPUs, GPUs, browsers, microcontrollers, FPGAs and more.

Automatically generate and optimize tensor operators on more backends.
  • {:.key-block} Flexibility


Need support for block sparsity, quantization (1,2,4,8 bit integers, posit), random forests/classical ML, memory planning, MISRA-C compatibility, Python prototyping or all of the above?

TVM’s flexible design enables all of these things and more.
  • {:.key-block} Ease of Use

Ease of Use

Compilation of deep learning models in Keras, MXNet, PyTorch, Tensorflow, CoreML, DarkNet and more. Start using TVM with Python today, build out production stacks using C++, Rust, or Java the next day.

  • {:.doc-link-block}


Written with care
& love for you.

  • {:.doc-link-block}


Join the TVM

  • {:.doc-link-block}


Read more about TVM
and our thinking