diff --git a/docs/dev/relay_add_op.rst b/docs/dev/relay_add_op.rst index 751e938fe0127c76458787d1f429f8f28214cac1..4a9625ce11980d88abd92eeb8d5b0f4ade0d1910 100644 --- a/docs/dev/relay_add_op.rst +++ b/docs/dev/relay_add_op.rst @@ -7,10 +7,8 @@ that they will be integrated into Relay's type system. Registering an operator requires three steps: -- Using the ``RELAY_REGISTER_OP`` macro in C++ to -register the operator's arity and type information -- Defining a C++ function to produce a call node for the -operator and registering a Python API hook for the function +- Using the ``RELAY_REGISTER_OP`` macro in C++ to register the operator's arity and type information +- Defining a C++ function to produce a call node for the operator and registering a Python API hook for the function - Wrapping the above Python API hook in a neater interface The file ``src/relay/op/tensor/binary.cc`` provides @@ -48,9 +46,7 @@ to specify the following information about an operator in Relay: - Arity (number of arguments) - Names and descriptions for positional arguments -- Support level (1 indicating an internal intrinsic, higher numbers -indicating operators that are not as integral to the framework or are -supported externally) +- Support level (1 indicates an internal intrinsic; higher numbers indicate less integral or externally supported operators) - A type relation for the operator The below example is from ``binary.cc`` and uses a broadcasting @@ -144,8 +140,6 @@ before producing the call node: Summary ------- -- A TVM operator can be registered in Relay using a relation to express -the appropriate type information. -- Using an operator in Relay requires a function to produce a -call node for the operator. +- A TVM operator can be registered in Relay using a relation to express the appropriate type information. +- Using an operator in Relay requires a function to produce a call node for the operator. - It is best to have a simple Python wrapper for producing the call node.