Functionlinear_attention_fwd_kernel(
realQ, imageQ, realK, imageK, realV, imageV, realO, imageO, # realP, imageP,
real_sm_scale, image_sm
examples/attention/triton/fused_linear_attention_complex_tile_k.py:19
Functionmatmul_kernel_tma_persistent(
a_desc_ptr,
b_desc_ptr,
c_desc_ptr, #
M,
N,
K, #
BLOCK_SIZE_M: tl.constexpr,
examples/matmul/triton/triton_matmul_sm90.py:71