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
{:.mb-3}
Compilation and minimal runtimes commonly unlock ML workloads on existing hardware.
- {:.key-block}
Run Everywhere
CPUs, GPUs, browsers, microcontrollers, FPGAs and more.
{:.mt-0.mt-lg-3}
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?
{:.mt-0.mt-lg-3}
TVM’s flexible design enables all of these things and more.
- {:.key-block}
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}
Docs
Written with care
& love for you.
- {:.doc-link-block}
Community
- {:.doc-link-block}