Module kernel 

Block-based iteration engine for strided permutation operations.

Structs

KernelPlan

Constants

SMALL_TENSOR_THRESHOLD

Maximum total elements for the small tensor fast path.

Functions

build_plan_fused

Build an execution plan with dimension fusion.

build_plan_fused_small

Simplified plan for small tensors that fit in L1 cache.

for_each_inner_block_preordered

Iterate over blocks with pre-ordered dimensions and initial offsets.

total_len

Utility: total number of elements.