tilelang.jit.adapter.base
=========================

.. py:module:: tilelang.jit.adapter.base

.. autoapi-nested-parse::

   The profiler and convert to torch utils



Classes
-------

.. autoapisummary::

   tilelang.jit.adapter.base.BaseKernelAdapter


Module Contents
---------------

.. py:class:: BaseKernelAdapter(mod, params, result_idx)

   Bases: :py:obj:`abc.ABC`


   Helper class that provides a standard way to create an ABC using
   inheritance.


   .. py:attribute:: func
      :type:  Callable | None
      :value: None



   .. py:attribute:: mod


   .. py:attribute:: params


   .. py:attribute:: result_idx


   .. py:method:: get_current_stream_functor()
      :staticmethod:


      Return a callable that reads Torch's current CUDA stream pointer.

      The returned lambda yields the raw CUDA stream handle of the current
      PyTorch stream on the active device. It's a thunk (evaluated at call
      time) so that any upstream stream guards are respected. If CUDA is
      unavailable, it returns a lambda that yields 0.



   .. py:method:: get_current_device_functor()
      :staticmethod:


      Return a callable that yields Torch's current device.

      Similar to the stream functor, we capture a callable that, when called,
      fetches the current device according to PyTorch. On CPU or when CUDA is
      unavailable, returns ``torch.device('cpu')``.



   .. py:method:: __call__(*args, **kwds)


   .. py:method:: get_kernel_source(kernel_only = True)