Skip to main content
Log in

Mojo function

top_k_fused_sampling_cpu

top_k_fused_sampling_cpu[type: DType, rank: Int, out_idx_type: DType](k: Int, input: NDBuffer[type, rank, origin], out_idxs: NDBuffer[out_idx_type, rank, origin], temperature: SIMD[type, 1] = __init__[__mlir_type.!pop.int_literal](1))

Generalized implementation of the Top K algorithm with sampling. Returns the sampled index from the innermost dimension of the input tensor for each row/subvolume.

Parameters:

  • type (DType): Data type of the input buffer.
  • rank (Int): Rank of the input.
  • out_idx_type (DType): Data type of the output indices.

Args:

  • k (Int): Int - Represents the K largest values to consider for sampling.
  • input (NDBuffer[type, rank, origin]): NDBuffer[type, rank] (Any shape)- The input tensor.
  • out_idxs (NDBuffer[out_idx_type, rank, origin]): NDBuffer[out_idx_type, rank] (shape of [input_shape[:-1]] + [1]) - The output indices.
  • temperature (SIMD[type, 1]): The temperature based scaling.