Packages

extorch

0.3.0
0.4.0 0.3.0 0.2.0 0.1.0-pre0

Production ML model serving on the BEAM. Serve PyTorch models faster than Python with pre-compiled graph execution, AOTI compiled inference, and OTP fault tolerance.

HexDocs

Current section

Files

Jump to
Readme
4 Versions
3 Dependencies
Dependants
Files
Activity
extorch lib extorch.ex
Raw

lib/extorch.ex 

defmodule ExTorch do

  @moduledoc """

  The ``ExTorch`` namespace contains data structures for multi-dimensional tensors and mathematical operations over these are defined.

  Additionally, it provides many utilities for efficient serializing of Tensors and arbitrary types, and other useful utilities.



  It has a CUDA counterpart, that enables you to run your tensor computations on an NVIDIA GPU with compute capability >= 3.0

  """

  use ExTorch.DelegateWithDocs

  import ExTorch.ModuleMixin



  # Native operations

  extends(ExTorch.Native.Tensor.Creation)

  extends(ExTorch.Native.Tensor.Ops.Manipulation)

  extends(ExTorch.Native.Tensor.Ops.Indexing)

  extends(ExTorch.Native.Tensor.Ops.PointWise)

  extends(ExTorch.Native.Tensor.Ops.Comparison)

  extends(ExTorch.Native.Tensor.Ops.Reduction)

  extends(ExTorch.Native.Tensor.Ops.Other)

  extends(ExTorch.Registry.DType)

  extends(ExTorch.Registry.Device)



  # extends(ExTorch.Native.Tensor.Info)

end