For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).

Mojo function

argmaxmin_gpu

def argmaxmin_gpu[dtype: DType, output_type: DType, largest: Bool](ctx: DeviceContext, input: TileTensor[dtype, Storage=input.Storage, address_space=input.address_space, linear_idx_type=input.linear_idx_type], output: TileTensor[output_type, Storage=output.Storage, address_space=output.address_space, linear_idx_type=output.linear_idx_type])

Wraps the Top-K GPU kernel with K=1 to perform argmax on the inner-most dimension.

Parameters:

• ​dtype (DType): DType - The data dtype of the input tensor.
• ​output_type (DType): DType - The data dtype of the output tensor.
• ​largest (Bool): Bool - Whether to perform argmax or argmin.