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

Mojo function

block_scales_interleave_fp4

def block_scales_interleave_fp4[scales_dtype: DType, //, *, SF_VECTOR_SIZE: Int = Int(16), num_max_threads: Int = Int(1024)](ctx: DeviceContext, input_scales_tile: TileTensor[scales_dtype, Storage=input_scales_tile.Storage, linear_idx_type=input_scales_tile.linear_idx_type], output_scales_tile: TileTensor[scales_dtype, Storage=output_scales_tile.Storage, linear_idx_type=output_scales_tile.linear_idx_type])

Launches the SM100 kernel that reinterleaves rank-2 scale factors into the 5D TCGEN layout.

Converts the flat scale-factor tensor into the interleaved 5D layout expected by the tensor-core scale-factor feed.

Parameters:

scales_dtype (DType): Element type of the block scale-factor tensors (inferred).
SF_VECTOR_SIZE (Int): Number of elements covered by each block scale factor (defaults to 16).
num_max_threads (Int): Maximum number of threads per block for the launch grid (defaults to 1024).