The nvmath.bindings module is experimental and potentially subject to future changes.

create_block_sparse_contraction

nvmath.bindings.cutensor.create_block_sparse_contraction(

intptr_t handle,

intptr_t desc_a,

mode_a,

int op_a,

intptr_t desc_b,

mode_b,

int op_b,

intptr_t desc_c,

mode_c,

int op_c,

intptr_t desc_d,

mode_d,

intptr_t desc_compute,

) → intptr_t

See cutensorCreateBlockSparseContraction.