* \brief Returns the cuda stream accociated with this context * \return the cuda stream */

* \brief Evaluates this into a matrix. * This evaluates any expression template. If this is already a matrix, it is returned unchanged. * \return

Loads the class's state. Args: state_dict (dict): scaler state. Should be an object returned from a call to :meth:

Converts a denoiser output to a Karras ODE derivative.

* \brief Returns the total number of entries in this matrix. * This value is computed as \code rows()*cols()*batches()* \endcode * \return the total

Returns the state of the class as a :class:`dict`.

* \return a deep clone of this sparsity pattern */

Calculates the noise level (sigma_down) to step down to and the amount of noise to add (sigma_up) when doing an ancestral sampling step.

Updates the step count.

Draws stratified samples from a uniform distribution, using settings from a context manager.

Given a 3D mesh and a set of query points, return closest point barycentrics Args: query_points: np.array (float) [Q, 3] query poi