1pub mod argmax;
6pub mod argsort;
7pub mod top_k;
8pub mod copy;
9pub mod cumsum;
10pub mod dense_gemm;
11pub mod dense_gemv_bf16;
12pub mod dense_mm_bf16;
13pub mod dense_mm_f16;
14pub mod dense_mm_f32_f32;
15pub mod elementwise;
16pub mod embedding;
17pub mod gather;
18pub mod gather_bench;
19pub mod hadamard;
20pub mod hadamard_quantize_kv;
21pub mod encode_helpers;
22pub mod fused_head_norm_rope;
23pub mod fused_norm_add;
24pub mod fused_residual_norm;
25pub mod gelu;
26pub mod kv_cache_copy;
27pub mod l2_norm;
28pub mod log_elementwise;
29pub mod row_sum;
30pub mod moe_dispatch;
31pub mod moe_gate;
32pub mod moe_softmax_topk;
33pub mod moe_weighted_reduce;
34pub mod qkv_split;
35pub mod repeat_tiled;
36pub mod quantized_matmul;
37pub mod quantized_matmul_ggml;
38pub mod quantized_matmul_id;
39pub mod quantized_matmul_id_ggml;
40pub mod rms_norm;
41pub mod rope;
42pub mod rope_multi;
43pub mod vision_2d_rope;
44pub mod scale_mask_softmax;
45pub mod sigmoid_mul;
46pub mod silu_mul;
47pub mod compute_g_beta;
48pub mod ssm_norm_gate;
49pub mod flash_attn_prefill;
50pub mod flash_attn_prefill_blk;
51pub mod flash_attn_prefill_d512;
52pub mod flash_attn_prefill_mask;
53pub mod flash_attn_vec;
54pub mod flash_attn_vec_tq;
55pub mod flash_attn_vec_tq_hb;
56pub mod fwht_standalone;
57pub mod chunk_gated_delta_rule;
58pub mod chunk_gated_delta_rule_tri_solve_invert;
59pub mod gated_delta_net;
60pub mod gated_delta_net_decode;
61pub mod gated_delta_net_chunk;
62pub mod gated_delta_net_chunk_o;
63pub mod gated_delta_net_kkt;
64pub mod gated_delta_net_recompute_wu;
65pub mod tq_dequantize_kv;
66pub mod sdpa;
67pub mod sdpa_decode;
68pub mod sdpa_sliding;
69pub mod softcap;
70pub mod softmax;
71pub mod softmax_backward;
72pub mod softmax_sample;
73pub mod ssm_conv;
74pub mod transpose;
75pub mod tri_solve;
76pub mod qdq_legacy;
77pub mod rms_norm_backward;
78pub mod slice_concat_2d;
79pub mod silu_backward;
80pub mod embedding_autograd;
81pub mod adam_update;
82pub mod qdq_affine;
83pub mod qmm_affine;
84pub mod im2col_2d_3ch;
86pub mod add_bias_row_2d;
87pub mod bilinear_resize_2d;
88pub mod block_merge_2x2;
89pub mod feature_concat;