kernel_add_id 168 0 0 183 1024
kernel_arange_f32 130 0 0 183 1024
kernel_argmax_f32 249 0 3 206 1024
kernel_argsort_f32_i32_asc 316 0 14 185 1024
kernel_argsort_f32_i32_desc 283 0 14 185 1024
kernel_argsort_merge_f32_i32_asc 748 0 0 186 1024
kernel_argsort_merge_f32_i32_desc 753 0 0 206 1024
kernel_bin_fuse_f16_f16_f16 FALLA_CONSTANTES
kernel_bin_fuse_f16_f16_f16_4 FALLA_CONSTANTES
kernel_bin_fuse_f32_f32_f32 FALLA_CONSTANTES
kernel_bin_fuse_f32_f32_f32_4 FALLA_CONSTANTES
kernel_col2im_1d_bf16 273 0 0 183 1024
kernel_col2im_1d_f16 270 0 0 182 1024
kernel_col2im_1d_f32 267 0 0 182 1024
kernel_concat_bf16 303 1 0 183 1024
kernel_concat_f16 278 1 0 206 1024
kernel_concat_f32 276 0 0 206 1024
kernel_concat_i16 278 1 0 206 1024
kernel_concat_i32 277 0 0 206 1024
kernel_concat_i64 278 0 0 206 1024
kernel_concat_i8 277 1 0 193 1024
kernel_conv_2d_dw_f16_f32 468 1 0 206 1024
kernel_conv_2d_dw_f32_f32 467 0 0 206 1024
kernel_conv_2d_dw_tiled_f16_f32 442 1 0 187 1024
kernel_conv_2d_dw_tiled_f32_f32 442 0 0 187 1024
kernel_conv_2d_f16_f32 1170 1 0 187 1024
kernel_conv_2d_f32_f32 1169 0 0 187 1024
kernel_conv_3d_f16_f32 907 1 0 187 1024
kernel_conv_3d_f32_f32 908 0 0 187 1024
kernel_conv_transpose_1d_f16_f32 266 0 0 187 1024
kernel_conv_transpose_1d_f32_f32 265 0 0 187 1024
kernel_conv_transpose_2d_f16_f32 779 0 2 187 1024
kernel_conv_transpose_2d_f32_f32 777 0 2 187 1024
kernel_count_equal_i32 FALLA_CONSTANTES
kernel_cpy_bf16_bf16 936 1 0 188 1024
kernel_cpy_bf16_f32 928 1 0 155 1024
kernel_cpy_contig_bf16_bf16 116 1 0 186 1024
kernel_cpy_contig_bf16_f32 154 0 0 186 1024
kernel_cpy_contig_f16_f16 124 1 0 186 1024
kernel_cpy_contig_f16_f32 124 0 0 186 1024
kernel_cpy_contig_f32_bf16 156 0 0 186 1024
kernel_cpy_contig_f32_f16 126 0 0 186 1024
kernel_cpy_contig_f32_f32 122 0 0 186 1024
kernel_cpy_contig_f32_i32 123 0 0 186 1024
kernel_cpy_contig_i32_f32 122 0 0 186 1024
kernel_cpy_contig_i32_i32 122 0 0 186 1024
kernel_cpy_f16_f16 966 1 0 188 1024
kernel_cpy_f16_f32 964 1 0 188 1024
kernel_cpy_f32_bf16 934 0 0 188 1024
kernel_cpy_f32_f16 966 0 0 188 1024
kernel_cpy_f32_f32 965 0 0 188 1024
kernel_cpy_f32_i32 964 0 0 188 1024
kernel_cpy_f32_iq4_nl 3307 0 0 188 1024
kernel_cpy_f32_q1_0 1343 8 0 188 1024
kernel_cpy_f32_q2_0 2397 64 0 188 1024
kernel_cpy_f32_q4_0 1416 0 0 188 1024
kernel_cpy_f32_q4_1 1457 0 0 188 1024
kernel_cpy_f32_q5_0 1609 0 0 188 1024
kernel_cpy_f32_q5_1 1555 0 0 188 1024
kernel_cpy_f32_q8_0 1431 0 0 188 1024
kernel_cpy_f32_turbo2 3652 8 0 232 448
kernel_cpy_f32_turbo3 3969 16 0 248 448
kernel_cpy_f32_turbo4 4253 8 0 252 448
kernel_cpy_i32_f32 964 0 0 188 1024
kernel_cpy_i32_i32 964 0 0 188 1024
kernel_cpy_q1_0_f16 1037 2 0 188 1024
kernel_cpy_q1_0_f32 1012 2 0 188 1024
kernel_cpy_q2_0_f16 1027 4 0 188 1024
kernel_cpy_q2_0_f32 1021 4 0 188 1024
kernel_cpy_q4_0_f16 1036 9 0 188 1024
kernel_cpy_q4_0_f32 1009 9 0 188 1024
kernel_cpy_q4_1_f16 1034 10 0 188 1024
kernel_cpy_q4_1_f32 1006 10 0 188 1024
kernel_cpy_q5_0_f16 1121 4 0 188 1024
kernel_cpy_q5_0_f32 1100 4 0 188 1024
kernel_cpy_q5_1_f16 1124 4 0 188 1024
kernel_cpy_q5_1_f32 1094 4 0 188 1024
kernel_cpy_q8_0_f16 1004 16 0 188 1024
kernel_cpy_q8_0_f32 1006 16 0 188 1024
kernel_cpy_turbo2_f32 2872 8 0 232 448
kernel_cpy_turbo3_f32 2951 16 0 248 448
kernel_cpy_turbo4_f32 2885 8 0 252 448
kernel_cumsum_add_f32 462 0 0 204 1024
kernel_cumsum_blk_f32 588 1 5 208 1024
kernel_diag_f32 159 0 0 179 1024
kernel_dsv4_hc_comb_f32 260 0 0 177 1024
kernel_dsv4_hc_post_f32 333 0 0 177 1024
kernel_dsv4_hc_pre_f32 233 0 0 183 1024
kernel_fwht_f32_128 277 0 0 186 1024
kernel_fwht_f32_128_w64 238 0 0 186 1024
kernel_fwht_f32_256 391 0 0 186 1024
kernel_fwht_f32_256_w64 307 0 0 186 1024
kernel_fwht_f32_512 627 0 0 186 1024
kernel_fwht_f32_512_w64 442 0 0 186 1024
kernel_fwht_f32_64 260 0 0 186 1024
kernel_fwht_f32_64_w64 243 0 0 186 1024
kernel_gated_delta_net_f32_1 FALLA_CONSTANTES
kernel_gated_delta_net_f32_2 FALLA_CONSTANTES
kernel_gated_delta_net_f32_4 FALLA_CONSTANTES
kernel_geglu_erf_f16 182 0 0 182 1024
kernel_geglu_erf_f32 180 0 0 182 1024
kernel_geglu_f16 270 0 0 182 1024
kernel_geglu_f32 268 0 0 182 1024
kernel_geglu_quick_f16 208 0 0 186 1024
kernel_geglu_quick_f32 208 0 0 186 1024
kernel_get_rows_bf16 213 0 0 187 1024
kernel_get_rows_f16 202 0 0 187 1024
kernel_get_rows_f32 201 0 0 187 1024
kernel_get_rows_i32 201 0 0 187 1024
kernel_get_rows_iq1_m 2025 12 0 187 1024
kernel_get_rows_iq1_s 1989 9 0 187 1024
kernel_get_rows_iq2_s 2039 6 0 187 1024
kernel_get_rows_iq2_xs 1224 5 0 251 1024
kernel_get_rows_iq2_xxs 859 7 0 251 1024
kernel_get_rows_iq3_s 825 8 0 187 1024
kernel_get_rows_iq3_xxs 651 10 0 251 1024
kernel_get_rows_iq4_nl 329 1 0 187 1024
kernel_get_rows_iq4_xs 357 1 0 187 1024
kernel_get_rows_mxfp4 393 17 0 187 1024
kernel_get_rows_q1_0 294 2 0 187 1024
kernel_get_rows_q2_0 305 4 0 187 1024
kernel_get_rows_q2_K 328 4 0 224 1024
kernel_get_rows_q3_K 415 4 0 192 1024
kernel_get_rows_q4_0 290 9 0 187 1024
kernel_get_rows_q4_1 292 10 0 187 1024
kernel_get_rows_q4_K 325 0 0 208 1024
kernel_get_rows_q5_0 383 4 0 187 1024
kernel_get_rows_q5_1 378 4 0 187 1024
kernel_get_rows_q5_K 416 7 0 187 1024
kernel_get_rows_q6_K 388 1 0 187 1024
kernel_get_rows_q8_0 289 16 0 187 1024
kernel_group_norm_f32 533 0 6 206 1024
kernel_im2col_ext_f16 572 0 0 204 1024
kernel_im2col_ext_f32 571 0 0 204 1024
kernel_im2col_f16 412 0 0 204 1024
kernel_im2col_f32 410 0 0 204 1024
kernel_l2_norm_f32_f32 271 0 3 183 1024
kernel_l2_norm_f32_f32_4 247 0 3 183 1024
kernel_lightning_indexer_bf16 FALLA_CONSTANTES
kernel_lightning_indexer_f16 FALLA_CONSTANTES
kernel_lightning_indexer_f32 FALLA_CONSTANTES
kernel_lightning_indexer_q4_0 FALLA_CONSTANTES
kernel_lightning_indexer_q4_1 FALLA_CONSTANTES
kernel_lightning_indexer_q5_0 FALLA_CONSTANTES
kernel_lightning_indexer_q5_1 FALLA_CONSTANTES
kernel_lightning_indexer_q8_0 FALLA_CONSTANTES
kernel_memset_i64 103 0 0 186 1024
kernel_norm_f32 307 0 5 185 1024
kernel_norm_f32_4 328 0 5 202 1024
kernel_norm_mul_add_f32 562 0 5 185 1024
kernel_norm_mul_add_f32_4 589 0 5 202 1024
kernel_norm_mul_f32 438 0 5 185 1024
kernel_norm_mul_f32_4 472 0 5 202 1024
kernel_op_sum_f32 231 0 2 206 1024
kernel_opt_step_adamw_f32 162 0 0 187 1024
kernel_opt_step_sgd_f32 122 0 0 186 1024
kernel_pad_f32 333 0 0 183 1024
kernel_pad_f32_4 318 0 0 182 1024
kernel_pad_reflect_1d_f32 226 0 0 204 1024
kernel_pool_1d_avg_f32 460 0 0 184 1024
kernel_pool_1d_max_f32 451 0 0 188 1024
kernel_pool_2d_avg_f32 535 0 0 184 1024
kernel_pool_2d_max_f32 530 0 0 188 1024
kernel_reglu_f16 166 1 0 182 1024
kernel_reglu_f32 164 0 0 200 1024
kernel_repeat_bf16 332 1 0 185 1024
kernel_repeat_f16 303 1 0 228 1024
kernel_repeat_f32 302 0 0 228 1024
kernel_repeat_i16 303 1 0 228 1024
kernel_repeat_i32 302 0 0 228 1024
kernel_rms_norm_f32 233 0 3 185 1024
kernel_rms_norm_f32_4 251 0 3 202 1024
kernel_rms_norm_mul_add_f32 493 0 3 185 1024
kernel_rms_norm_mul_add_f32_4 511 0 3 202 1024
kernel_rms_norm_mul_f32 373 0 3 185 1024
kernel_rms_norm_mul_f32_4 390 0 3 220 1024
kernel_roll_f32 174 0 0 182 1024
kernel_rope_multi_f16 FALLA_CONSTANTES
kernel_rope_multi_f32 FALLA_CONSTANTES
kernel_rope_neox_f16 FALLA_CONSTANTES
kernel_rope_neox_f32 FALLA_CONSTANTES
kernel_rope_norm_f16 FALLA_CONSTANTES
kernel_rope_norm_f32 FALLA_CONSTANTES
kernel_rope_vision_f16 FALLA_CONSTANTES
kernel_rope_vision_f32 FALLA_CONSTANTES
kernel_rwkv_wkv6_f32 1161 0 67 187 512
kernel_rwkv_wkv7_f32 953 0 83 187 576
kernel_set_rows_bf16_i32_bf16 303 1 0 218 1024
kernel_set_rows_bf16_i64_bf16 304 1 0 218 1024
kernel_set_rows_f16_i32_f16 295 1 0 187 1024
kernel_set_rows_f16_i64_f16 295 1 0 187 1024
kernel_set_rows_f32_i32_bf16 311 0 0 187 1024
kernel_set_rows_f32_i32_f16 297 0 0 187 1024
kernel_set_rows_f32_i32_f32 295 0 0 187 1024
kernel_set_rows_f32_i32_iq4_nl 2627 0 0 187 1024
kernel_set_rows_f32_i32_q4_0 798 0 0 187 1024
kernel_set_rows_f32_i32_q4_1 833 0 0 187 1024
kernel_set_rows_f32_i32_q5_0 980 0 0 187 1024
kernel_set_rows_f32_i32_q5_1 914 0 0 187 1024
kernel_set_rows_f32_i32_q8_0 778 0 0 187 1024
kernel_set_rows_f32_i64_bf16 312 0 0 187 1024
kernel_set_rows_f32_i64_f16 297 0 0 187 1024
kernel_set_rows_f32_i64_f32 295 0 0 187 1024
kernel_set_rows_f32_i64_iq4_nl 2627 0 0 187 1024
kernel_set_rows_f32_i64_q4_0 799 0 0 187 1024
kernel_set_rows_f32_i64_q4_1 834 0 0 187 1024
kernel_set_rows_f32_i64_q5_0 981 0 0 187 1024
kernel_set_rows_f32_i64_q5_1 915 0 0 187 1024
kernel_set_rows_f32_i64_q8_0 779 0 0 187 1024
kernel_set_rows_turbo2_i32 3530 8 0 232 448
kernel_set_rows_turbo2_i64 3531 8 0 232 448
kernel_set_rows_turbo3_i32 846 0 0 248 1024
kernel_set_rows_turbo3_i32_w64 748 0 0 248 1024
kernel_set_rows_turbo3_i64 843 0 0 248 1024
kernel_set_rows_turbo3_i64_w64 747 0 0 248 1024
kernel_set_rows_turbo4_i32 1017 0 0 252 1024
kernel_set_rows_turbo4_i32_w64 813 0 0 252 1024
kernel_set_rows_turbo4_i64 1013 0 0 252 1024
kernel_set_rows_turbo4_i64_w64 812 0 0 252 1024
kernel_silu_back_f32 131 0 0 186 1024
kernel_snake_bf16 181 0 0 183 1024
kernel_snake_f16 182 0 0 224 1024
kernel_snake_f32 179 0 0 183 1024
kernel_soft_max_f16 537 0 6 188 1024
kernel_soft_max_f16_4 592 0 6 222 1024
kernel_soft_max_f32 528 0 6 188 1024
kernel_soft_max_f32_4 583 0 6 202 1024
kernel_solve_tri_f32 FALLA_CONSTANTES
kernel_ssm_conv_f32_f32 147 0 0 187 1024
kernel_ssm_conv_f32_f32_4 164 0 0 206 1024
kernel_ssm_conv_f32_f32_batched FALLA_CONSTANTES
kernel_ssm_conv_f32_f32_batched_4 FALLA_CONSTANTES
kernel_ssm_conv_f32_f32_decode 198 0 0 187 1024
kernel_ssm_conv_f32_f32_decode_4 179 0 0 192 1024
kernel_ssm_conv_f32_f32_decode_silu 171 0 0 187 1024
kernel_ssm_conv_f32_f32_decode_silu_4 187 0 0 206 1024
kernel_ssm_scan_f32 702 0 7 183 1024
kernel_sum_rows_f32_f32 FALLA_CONSTANTES
kernel_sum_rows_f32_f32_4 FALLA_CONSTANTES
kernel_swiglu_f16 171 0 0 187 1024
kernel_swiglu_f32 170 0 0 187 1024
kernel_swiglu_oai_f16 172 0 0 187 1024
kernel_swiglu_oai_f32 171 0 0 187 1024
kernel_timestep_embedding_f32 178 0 0 186 1024
kernel_topk_moe_f32 757 0 51 184 1024
kernel_tri_bf16_0 173 0 0 204 1024
kernel_tri_bf16_1 173 0 0 204 1024
kernel_tri_bf16_2 173 0 0 204 1024
kernel_tri_bf16_3 173 0 0 204 1024
kernel_tri_f16_0 173 1 0 185 1024
kernel_tri_f16_1 173 1 0 185 1024
kernel_tri_f16_2 172 1 0 185 1024
kernel_tri_f16_3 172 1 0 185 1024
kernel_tri_f32_0 170 0 0 185 1024
kernel_tri_f32_1 170 0 0 185 1024
kernel_tri_f32_2 169 0 0 185 1024
kernel_tri_f32_3 169 0 0 185 1024
kernel_turbo_wht 2627 192 0 186 768
kernel_unary_f16_f16 FALLA_CONSTANTES
kernel_unary_f16_f16_4 FALLA_CONSTANTES
kernel_unary_f32_f32 FALLA_CONSTANTES
kernel_unary_f32_f32_4 FALLA_CONSTANTES
kernel_upscale_bicubic_f32 761 0 0 183 1024
kernel_upscale_bilinear_f32 FALLA_CONSTANTES
kernel_upscale_nearest_f32 369 0 0 186 1024
