Hugging Face's logo

electroglyph
/
KnowLine-4B-Gen5.5-onnx

Text Classification
ONNX
onnxruntime
decision-model
qwen3.5
Model card Files
xet
 Community
KnowLine-4B-Gen5.5-onnx
File size: 245,189 Bytes
7d5fc54
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
Valid precision + execution provider combinations are: FP32 CPU, FP32 CUDA, FP16 CUDA, FP16 DML, FP16 TRT-RTX, BF16 CUDA, BF16 TRT-RTX, INT8 CPU, INT8 CUDA, INT8 WebGPU, INT4 CPU, INT4 CUDA, INT4 DML, INT4 WebGPU
Extra options: {'accuracy_level': '4', 'block_size': '32'}
GroupQueryAttention (GQA) is used in this model.
GroupQueryAttention (GQA) is used in this model.

Loading weights:   0%|          | 0/426 [00:00<?, ?it/s]
Loading weights: 100%|██████████| 426/426 [00:00<00:00, 21187.62it/s]
2026-11-05 03:42:47,294 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/constant_nodes/INT64/[1] ...
2026-11-05 03:42:47,294 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/attn_mask_reformat/attn_mask_subgraph/ReduceSum ...
2026-11-05 03:42:47,294 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/attn_mask_reformat/attn_mask_subgraph/Sub ...
2026-11-05 03:42:47,294 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/attn_mask_reformat/attn_mask_subgraph/Sub/Cast ...
2026-11-05 03:42:47,294 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/attn_mask_reformat/attn_mask_subgraph/Shape ...
2026-11-05 03:42:47,294 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/constant_nodes/INT64/1 ...
2026-11-05 03:42:47,294 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/attn_mask_reformat/attn_mask_subgraph/Gather ...
2026-11-05 03:42:47,294 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - Gather doesn't have const weight. Skip quantization.
2026-11-05 03:42:47,294 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/attn_mask_reformat/attn_mask_subgraph/Gather with 4 bits ...
2026-11-05 03:42:47,294 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/attn_mask_reformat/attn_mask_subgraph/Gather/Cast ...
2026-11-05 03:42:47,294 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/constant_nodes/INT64/[248320, 1280] ...
2026-11-05 03:42:47,294 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/embed_tokens/Reshape ...
2026-11-05 03:42:47,294 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/embed_tokens/GatherBlockQuantized ...
2026-11-05 03:42:47,294 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/input_layernorm/LayerNorm ...
2026-11-05 03:42:47,294 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.0/linear_attn/qkv_proj/MatMul ...
2026-11-05 03:42:47,348 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.0/linear_attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:47,348 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.0/linear_attn/z_proj/MatMul ...
2026-11-05 03:42:47,370 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.0/linear_attn/z_proj/MatMul with 4 bits ...
2026-11-05 03:42:47,370 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.0/linear_attn/b_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:47,370 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.0/linear_attn/a_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:47,370 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/linear_attn/qkv_proj/Transpose ...
2026-11-05 03:42:47,370 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/linear_attn/CausalConvWithState ...
2026-11-05 03:42:47,370 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/linear_attn/conv_out/Transpose ...
2026-11-05 03:42:47,370 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/constant_nodes/INT64/[2048, 2048, 4096] ...
2026-11-05 03:42:47,370 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/linear_attn/split_qkv/Split ...
2026-11-05 03:42:47,370 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/constant_nodes/INT64/[0, 0, 16, 128] ...
2026-11-05 03:42:47,370 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/linear_attn/q_l2norm/flat/Reshape ...
2026-11-05 03:42:47,370 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/linear_attn/q_l2norm/LpNormalization ...
2026-11-05 03:42:47,370 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/constant_nodes/INT64/[0, 0, 2048] ...
2026-11-05 03:42:47,370 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/linear_attn/q_l2norm/unflat/Reshape ...
2026-11-05 03:42:47,370 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/linear_attn/k_l2norm/flat/Reshape ...
2026-11-05 03:42:47,370 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/linear_attn/k_l2norm/LpNormalization ...
2026-11-05 03:42:47,370 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/linear_attn/k_l2norm/unflat/Reshape ...
2026-11-05 03:42:47,370 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/constant_nodes/FLOAT/0.08838834764831843 ...
2026-11-05 03:42:47,370 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/linear_attn/q_scaled/Mul ...
2026-11-05 03:42:47,370 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/linear_attn/LinearAttentionGate ...
2026-11-05 03:42:47,370 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/linear_attn/LinearAttention ...
2026-11-05 03:42:47,370 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/linear_attn/GatedRMSNorm ...
2026-11-05 03:42:47,370 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.0/linear_attn/out_proj/MatMul ...
2026-11-05 03:42:47,399 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.0/linear_attn/out_proj/MatMul with 4 bits ...
2026-11-05 03:42:47,399 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:47,399 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.0/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:47,541 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.0/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:47,541 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/mlp/gate_up_proj/Split ...
2026-11-05 03:42:47,541 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:47,541 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/mlp/act_fn/Mul ...
2026-11-05 03:42:47,541 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/mlp/Mul ...
2026-11-05 03:42:47,541 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.0/mlp/down_proj/MatMul ...
2026-11-05 03:42:47,586 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.0/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:47,586 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.1/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:47,586 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.1/linear_attn/qkv_proj/MatMul ...
2026-11-05 03:42:47,632 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.1/linear_attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:47,632 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.1/linear_attn/z_proj/MatMul ...
2026-11-05 03:42:47,654 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.1/linear_attn/z_proj/MatMul with 4 bits ...
2026-11-05 03:42:47,654 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.1/linear_attn/b_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:47,654 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.1/linear_attn/a_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:47,654 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.1/linear_attn/qkv_proj/Transpose ...
2026-11-05 03:42:47,654 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.1/linear_attn/CausalConvWithState ...
2026-11-05 03:42:47,654 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.1/linear_attn/conv_out/Transpose ...
2026-11-05 03:42:47,654 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.1/linear_attn/split_qkv/Split ...
2026-11-05 03:42:47,654 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.1/linear_attn/q_l2norm/flat/Reshape ...
2026-11-05 03:42:47,654 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.1/linear_attn/q_l2norm/LpNormalization ...
2026-11-05 03:42:47,654 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.1/linear_attn/q_l2norm/unflat/Reshape ...
2026-11-05 03:42:47,654 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.1/linear_attn/k_l2norm/flat/Reshape ...
2026-11-05 03:42:47,654 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.1/linear_attn/k_l2norm/LpNormalization ...
2026-11-05 03:42:47,654 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.1/linear_attn/k_l2norm/unflat/Reshape ...
2026-11-05 03:42:47,654 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.1/linear_attn/q_scaled/Mul ...
2026-11-05 03:42:47,654 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.1/linear_attn/LinearAttentionGate ...
2026-11-05 03:42:47,654 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.1/linear_attn/LinearAttention ...
2026-11-05 03:42:47,654 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.1/linear_attn/GatedRMSNorm ...
2026-11-05 03:42:47,654 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.1/linear_attn/out_proj/MatMul ...
2026-11-05 03:42:47,698 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.1/linear_attn/out_proj/MatMul with 4 bits ...
2026-11-05 03:42:47,698 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.1/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:47,698 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.1/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:47,836 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.1/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:47,836 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.1/mlp/gate_up_proj/Split ...
2026-11-05 03:42:47,836 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.1/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:47,836 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.1/mlp/act_fn/Mul ...
2026-11-05 03:42:47,836 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.1/mlp/Mul ...
2026-11-05 03:42:47,836 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.1/mlp/down_proj/MatMul ...
2026-11-05 03:42:47,882 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.1/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:47,882 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.2/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:47,882 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.2/linear_attn/qkv_proj/MatMul ...
2026-11-05 03:42:47,931 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.2/linear_attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:47,931 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.2/linear_attn/z_proj/MatMul ...
2026-11-05 03:42:47,953 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.2/linear_attn/z_proj/MatMul with 4 bits ...
2026-11-05 03:42:47,953 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.2/linear_attn/b_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:47,953 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.2/linear_attn/a_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:47,953 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.2/linear_attn/qkv_proj/Transpose ...
2026-11-05 03:42:47,953 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.2/linear_attn/CausalConvWithState ...
2026-11-05 03:42:47,953 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.2/linear_attn/conv_out/Transpose ...
2026-11-05 03:42:47,953 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.2/linear_attn/split_qkv/Split ...
2026-11-05 03:42:47,953 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.2/linear_attn/q_l2norm/flat/Reshape ...
2026-11-05 03:42:47,953 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.2/linear_attn/q_l2norm/LpNormalization ...
2026-11-05 03:42:47,953 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.2/linear_attn/q_l2norm/unflat/Reshape ...
2026-11-05 03:42:47,953 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.2/linear_attn/k_l2norm/flat/Reshape ...
2026-11-05 03:42:47,953 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.2/linear_attn/k_l2norm/LpNormalization ...
2026-11-05 03:42:47,953 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.2/linear_attn/k_l2norm/unflat/Reshape ...
2026-11-05 03:42:47,953 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.2/linear_attn/q_scaled/Mul ...
2026-11-05 03:42:47,953 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.2/linear_attn/LinearAttentionGate ...
2026-11-05 03:42:47,953 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.2/linear_attn/LinearAttention ...
2026-11-05 03:42:47,953 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.2/linear_attn/GatedRMSNorm ...
2026-11-05 03:42:47,953 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.2/linear_attn/out_proj/MatMul ...
2026-11-05 03:42:47,974 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.2/linear_attn/out_proj/MatMul with 4 bits ...
2026-11-05 03:42:47,974 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.2/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:47,974 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.2/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:48,104 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.2/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:48,104 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.2/mlp/gate_up_proj/Split ...
2026-11-05 03:42:48,104 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.2/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:48,104 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.2/mlp/act_fn/Mul ...
2026-11-05 03:42:48,104 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.2/mlp/Mul ...
2026-11-05 03:42:48,104 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.2/mlp/down_proj/MatMul ...
2026-11-05 03:42:48,147 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.2/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:48,147 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.3/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:48,147 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.3/attn/qkv_proj/MatMul ...
2026-11-05 03:42:48,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.3/attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:48,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/constant_nodes/INT64/[8192, 1024, 1024] ...
2026-11-05 03:42:48,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.3/attn/qkv_proj/Split ...
2026-11-05 03:42:48,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/constant_nodes/INT64/[0, 0, 16, 512] ...
2026-11-05 03:42:48,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.3/attn/q_gate/Reshape ...
2026-11-05 03:42:48,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/constant_nodes/INT64/[256, 256] ...
2026-11-05 03:42:48,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.3/attn/q_gate/Split ...
2026-11-05 03:42:48,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/constant_nodes/INT64/[0, 0, 4096] ...
2026-11-05 03:42:48,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.3/attn/q_proj/Reshape ...
2026-11-05 03:42:48,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.3/attn/gate/Reshape ...
2026-11-05 03:42:48,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/constant_nodes/INT64/[0, -1, 256] ...
2026-11-05 03:42:48,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.3/attn/q_norm/Reshape_1 ...
2026-11-05 03:42:48,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.3/attn/q_norm/SimplifiedLayerNormalization ...
2026-11-05 03:42:48,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/constant_nodes/INT64/[0, -1, 4096] ...
2026-11-05 03:42:48,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.3/attn/q_norm/Reshape_2 ...
2026-11-05 03:42:48,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.3/attn/k_norm/Reshape_1 ...
2026-11-05 03:42:48,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.3/attn/k_norm/SimplifiedLayerNormalization ...
2026-11-05 03:42:48,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/constant_nodes/INT64/[0, -1, 1024] ...
2026-11-05 03:42:48,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.3/attn/k_norm/Reshape_2 ...
2026-11-05 03:42:48,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.3/attn/q_rotary/MRotaryEmbedding ...
2026-11-05 03:42:48,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.3/attn/k_rotary/MRotaryEmbedding ...
2026-11-05 03:42:48,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.3/attn/GroupQueryAttention ...
2026-11-05 03:42:48,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.3/attn/gate/Sigmoid ...
2026-11-05 03:42:48,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.3/attn/gate/Mul ...
2026-11-05 03:42:48,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.3/attn/o_proj/MatMul ...
2026-11-05 03:42:48,213 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.3/attn/o_proj/MatMul with 4 bits ...
2026-11-05 03:42:48,213 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.3/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:48,213 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.3/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:48,349 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.3/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:48,349 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.3/mlp/gate_up_proj/Split ...
2026-11-05 03:42:48,349 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.3/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:48,349 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.3/mlp/act_fn/Mul ...
2026-11-05 03:42:48,349 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.3/mlp/Mul ...
2026-11-05 03:42:48,349 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.3/mlp/down_proj/MatMul ...
2026-11-05 03:42:48,398 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.3/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:48,398 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.4/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:48,398 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.4/linear_attn/qkv_proj/MatMul ...
2026-11-05 03:42:48,443 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.4/linear_attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:48,443 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.4/linear_attn/z_proj/MatMul ...
2026-11-05 03:42:48,473 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.4/linear_attn/z_proj/MatMul with 4 bits ...
2026-11-05 03:42:48,473 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.4/linear_attn/b_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:48,473 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.4/linear_attn/a_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:48,473 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.4/linear_attn/qkv_proj/Transpose ...
2026-11-05 03:42:48,473 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.4/linear_attn/CausalConvWithState ...
2026-11-05 03:42:48,473 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.4/linear_attn/conv_out/Transpose ...
2026-11-05 03:42:48,473 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.4/linear_attn/split_qkv/Split ...
2026-11-05 03:42:48,473 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.4/linear_attn/q_l2norm/flat/Reshape ...
2026-11-05 03:42:48,473 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.4/linear_attn/q_l2norm/LpNormalization ...
2026-11-05 03:42:48,473 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.4/linear_attn/q_l2norm/unflat/Reshape ...
2026-11-05 03:42:48,473 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.4/linear_attn/k_l2norm/flat/Reshape ...
2026-11-05 03:42:48,473 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.4/linear_attn/k_l2norm/LpNormalization ...
2026-11-05 03:42:48,473 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.4/linear_attn/k_l2norm/unflat/Reshape ...
2026-11-05 03:42:48,473 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.4/linear_attn/q_scaled/Mul ...
2026-11-05 03:42:48,473 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.4/linear_attn/LinearAttentionGate ...
2026-11-05 03:42:48,473 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.4/linear_attn/LinearAttention ...
2026-11-05 03:42:48,473 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.4/linear_attn/GatedRMSNorm ...
2026-11-05 03:42:48,473 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.4/linear_attn/out_proj/MatMul ...
2026-11-05 03:42:48,494 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.4/linear_attn/out_proj/MatMul with 4 bits ...
2026-11-05 03:42:48,494 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.4/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:48,494 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.4/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:48,642 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.4/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:48,642 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.4/mlp/gate_up_proj/Split ...
2026-11-05 03:42:48,642 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.4/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:48,642 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.4/mlp/act_fn/Mul ...
2026-11-05 03:42:48,642 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.4/mlp/Mul ...
2026-11-05 03:42:48,642 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.4/mlp/down_proj/MatMul ...
2026-11-05 03:42:48,686 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.4/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:48,686 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.5/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:48,686 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.5/linear_attn/qkv_proj/MatMul ...
2026-11-05 03:42:48,733 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.5/linear_attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:48,733 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.5/linear_attn/z_proj/MatMul ...
2026-11-05 03:42:48,755 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.5/linear_attn/z_proj/MatMul with 4 bits ...
2026-11-05 03:42:48,755 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.5/linear_attn/b_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:48,755 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.5/linear_attn/a_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:48,755 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.5/linear_attn/qkv_proj/Transpose ...
2026-11-05 03:42:48,755 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.5/linear_attn/CausalConvWithState ...
2026-11-05 03:42:48,755 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.5/linear_attn/conv_out/Transpose ...
2026-11-05 03:42:48,755 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.5/linear_attn/split_qkv/Split ...
2026-11-05 03:42:48,755 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.5/linear_attn/q_l2norm/flat/Reshape ...
2026-11-05 03:42:48,755 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.5/linear_attn/q_l2norm/LpNormalization ...
2026-11-05 03:42:48,755 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.5/linear_attn/q_l2norm/unflat/Reshape ...
2026-11-05 03:42:48,755 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.5/linear_attn/k_l2norm/flat/Reshape ...
2026-11-05 03:42:48,755 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.5/linear_attn/k_l2norm/LpNormalization ...
2026-11-05 03:42:48,755 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.5/linear_attn/k_l2norm/unflat/Reshape ...
2026-11-05 03:42:48,755 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.5/linear_attn/q_scaled/Mul ...
2026-11-05 03:42:48,755 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.5/linear_attn/LinearAttentionGate ...
2026-11-05 03:42:48,755 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.5/linear_attn/LinearAttention ...
2026-11-05 03:42:48,755 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.5/linear_attn/GatedRMSNorm ...
2026-11-05 03:42:48,755 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.5/linear_attn/out_proj/MatMul ...
2026-11-05 03:42:48,777 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.5/linear_attn/out_proj/MatMul with 4 bits ...
2026-11-05 03:42:48,777 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.5/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:48,777 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.5/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:48,935 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.5/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:48,935 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.5/mlp/gate_up_proj/Split ...
2026-11-05 03:42:48,935 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.5/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:48,935 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.5/mlp/act_fn/Mul ...
2026-11-05 03:42:48,935 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.5/mlp/Mul ...
2026-11-05 03:42:48,935 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.5/mlp/down_proj/MatMul ...
2026-11-05 03:42:48,997 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.5/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:48,998 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.6/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:48,998 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.6/linear_attn/qkv_proj/MatMul ...
2026-11-05 03:42:49,045 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.6/linear_attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:49,045 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.6/linear_attn/z_proj/MatMul ...
2026-11-05 03:42:49,068 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.6/linear_attn/z_proj/MatMul with 4 bits ...
2026-11-05 03:42:49,068 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.6/linear_attn/b_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:49,068 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.6/linear_attn/a_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:49,068 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.6/linear_attn/qkv_proj/Transpose ...
2026-11-05 03:42:49,068 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.6/linear_attn/CausalConvWithState ...
2026-11-05 03:42:49,068 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.6/linear_attn/conv_out/Transpose ...
2026-11-05 03:42:49,068 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.6/linear_attn/split_qkv/Split ...
2026-11-05 03:42:49,068 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.6/linear_attn/q_l2norm/flat/Reshape ...
2026-11-05 03:42:49,068 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.6/linear_attn/q_l2norm/LpNormalization ...
2026-11-05 03:42:49,068 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.6/linear_attn/q_l2norm/unflat/Reshape ...
2026-11-05 03:42:49,068 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.6/linear_attn/k_l2norm/flat/Reshape ...
2026-11-05 03:42:49,068 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.6/linear_attn/k_l2norm/LpNormalization ...
2026-11-05 03:42:49,068 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.6/linear_attn/k_l2norm/unflat/Reshape ...
2026-11-05 03:42:49,068 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.6/linear_attn/q_scaled/Mul ...
2026-11-05 03:42:49,068 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.6/linear_attn/LinearAttentionGate ...
2026-11-05 03:42:49,068 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.6/linear_attn/LinearAttention ...
2026-11-05 03:42:49,068 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.6/linear_attn/GatedRMSNorm ...
2026-11-05 03:42:49,068 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.6/linear_attn/out_proj/MatMul ...
2026-11-05 03:42:49,090 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.6/linear_attn/out_proj/MatMul with 4 bits ...
2026-11-05 03:42:49,090 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.6/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:49,090 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.6/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:49,245 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.6/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:49,245 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.6/mlp/gate_up_proj/Split ...
2026-11-05 03:42:49,245 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.6/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:49,245 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.6/mlp/act_fn/Mul ...
2026-11-05 03:42:49,245 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.6/mlp/Mul ...
2026-11-05 03:42:49,245 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.6/mlp/down_proj/MatMul ...
2026-11-05 03:42:49,299 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.6/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:49,299 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.7/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:49,299 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.7/attn/qkv_proj/MatMul ...
2026-11-05 03:42:49,379 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.7/attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:49,379 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.7/attn/qkv_proj/Split ...
2026-11-05 03:42:49,379 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.7/attn/q_gate/Reshape ...
2026-11-05 03:42:49,379 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.7/attn/q_gate/Split ...
2026-11-05 03:42:49,379 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.7/attn/q_proj/Reshape ...
2026-11-05 03:42:49,379 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.7/attn/gate/Reshape ...
2026-11-05 03:42:49,379 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.7/attn/q_norm/Reshape_1 ...
2026-11-05 03:42:49,379 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.7/attn/q_norm/SimplifiedLayerNormalization ...
2026-11-05 03:42:49,379 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.7/attn/q_norm/Reshape_2 ...
2026-11-05 03:42:49,379 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.7/attn/k_norm/Reshape_1 ...
2026-11-05 03:42:49,379 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.7/attn/k_norm/SimplifiedLayerNormalization ...
2026-11-05 03:42:49,379 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.7/attn/k_norm/Reshape_2 ...
2026-11-05 03:42:49,379 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.7/attn/q_rotary/MRotaryEmbedding ...
2026-11-05 03:42:49,379 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.7/attn/k_rotary/MRotaryEmbedding ...
2026-11-05 03:42:49,379 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.7/attn/GroupQueryAttention ...
2026-11-05 03:42:49,379 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.7/attn/gate/Sigmoid ...
2026-11-05 03:42:49,379 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.7/attn/gate/Mul ...
2026-11-05 03:42:49,379 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.7/attn/o_proj/MatMul ...
2026-11-05 03:42:49,398 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.7/attn/o_proj/MatMul with 4 bits ...
2026-11-05 03:42:49,398 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.7/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:49,398 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.7/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:49,547 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.7/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:49,547 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.7/mlp/gate_up_proj/Split ...
2026-11-05 03:42:49,547 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.7/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:49,547 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.7/mlp/act_fn/Mul ...
2026-11-05 03:42:49,547 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.7/mlp/Mul ...
2026-11-05 03:42:49,547 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.7/mlp/down_proj/MatMul ...
2026-11-05 03:42:49,620 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.7/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:49,620 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.8/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:49,620 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.8/linear_attn/qkv_proj/MatMul ...
2026-11-05 03:42:49,668 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.8/linear_attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:49,668 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.8/linear_attn/z_proj/MatMul ...
2026-11-05 03:42:49,691 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.8/linear_attn/z_proj/MatMul with 4 bits ...
2026-11-05 03:42:49,692 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.8/linear_attn/b_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:49,692 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.8/linear_attn/a_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:49,692 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.8/linear_attn/qkv_proj/Transpose ...
2026-11-05 03:42:49,692 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.8/linear_attn/CausalConvWithState ...
2026-11-05 03:42:49,692 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.8/linear_attn/conv_out/Transpose ...
2026-11-05 03:42:49,692 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.8/linear_attn/split_qkv/Split ...
2026-11-05 03:42:49,692 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.8/linear_attn/q_l2norm/flat/Reshape ...
2026-11-05 03:42:49,692 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.8/linear_attn/q_l2norm/LpNormalization ...
2026-11-05 03:42:49,692 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.8/linear_attn/q_l2norm/unflat/Reshape ...
2026-11-05 03:42:49,692 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.8/linear_attn/k_l2norm/flat/Reshape ...
2026-11-05 03:42:49,692 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.8/linear_attn/k_l2norm/LpNormalization ...
2026-11-05 03:42:49,692 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.8/linear_attn/k_l2norm/unflat/Reshape ...
2026-11-05 03:42:49,692 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.8/linear_attn/q_scaled/Mul ...
2026-11-05 03:42:49,692 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.8/linear_attn/LinearAttentionGate ...
2026-11-05 03:42:49,692 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.8/linear_attn/LinearAttention ...
2026-11-05 03:42:49,692 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.8/linear_attn/GatedRMSNorm ...
2026-11-05 03:42:49,692 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.8/linear_attn/out_proj/MatMul ...
2026-11-05 03:42:49,714 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.8/linear_attn/out_proj/MatMul with 4 bits ...
2026-11-05 03:42:49,714 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.8/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:49,714 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.8/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:49,867 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.8/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:49,867 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.8/mlp/gate_up_proj/Split ...
2026-11-05 03:42:49,867 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.8/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:49,867 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.8/mlp/act_fn/Mul ...
2026-11-05 03:42:49,867 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.8/mlp/Mul ...
2026-11-05 03:42:49,867 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.8/mlp/down_proj/MatMul ...
2026-11-05 03:42:49,954 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.8/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:49,954 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.9/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:49,954 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.9/linear_attn/qkv_proj/MatMul ...
2026-11-05 03:42:49,992 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.9/linear_attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:49,992 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.9/linear_attn/z_proj/MatMul ...
2026-11-05 03:42:50,014 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.9/linear_attn/z_proj/MatMul with 4 bits ...
2026-11-05 03:42:50,015 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.9/linear_attn/b_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:50,015 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.9/linear_attn/a_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:50,015 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.9/linear_attn/qkv_proj/Transpose ...
2026-11-05 03:42:50,015 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.9/linear_attn/CausalConvWithState ...
2026-11-05 03:42:50,015 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.9/linear_attn/conv_out/Transpose ...
2026-11-05 03:42:50,015 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.9/linear_attn/split_qkv/Split ...
2026-11-05 03:42:50,015 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.9/linear_attn/q_l2norm/flat/Reshape ...
2026-11-05 03:42:50,015 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.9/linear_attn/q_l2norm/LpNormalization ...
2026-11-05 03:42:50,015 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.9/linear_attn/q_l2norm/unflat/Reshape ...
2026-11-05 03:42:50,015 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.9/linear_attn/k_l2norm/flat/Reshape ...
2026-11-05 03:42:50,015 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.9/linear_attn/k_l2norm/LpNormalization ...
2026-11-05 03:42:50,015 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.9/linear_attn/k_l2norm/unflat/Reshape ...
2026-11-05 03:42:50,015 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.9/linear_attn/q_scaled/Mul ...
2026-11-05 03:42:50,015 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.9/linear_attn/LinearAttentionGate ...
2026-11-05 03:42:50,015 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.9/linear_attn/LinearAttention ...
2026-11-05 03:42:50,015 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.9/linear_attn/GatedRMSNorm ...
2026-11-05 03:42:50,015 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.9/linear_attn/out_proj/MatMul ...
2026-11-05 03:42:50,039 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.9/linear_attn/out_proj/MatMul with 4 bits ...
2026-11-05 03:42:50,039 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.9/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:50,039 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.9/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:50,207 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.9/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:50,208 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.9/mlp/gate_up_proj/Split ...
2026-11-05 03:42:50,208 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.9/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:50,208 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.9/mlp/act_fn/Mul ...
2026-11-05 03:42:50,208 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.9/mlp/Mul ...
2026-11-05 03:42:50,208 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.9/mlp/down_proj/MatMul ...
2026-11-05 03:42:50,270 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.9/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:50,270 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.10/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:50,270 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.10/linear_attn/qkv_proj/MatMul ...
2026-11-05 03:42:50,315 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.10/linear_attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:50,315 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.10/linear_attn/z_proj/MatMul ...
2026-11-05 03:42:50,338 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.10/linear_attn/z_proj/MatMul with 4 bits ...
2026-11-05 03:42:50,338 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.10/linear_attn/b_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:50,338 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.10/linear_attn/a_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:50,338 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.10/linear_attn/qkv_proj/Transpose ...
2026-11-05 03:42:50,338 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.10/linear_attn/CausalConvWithState ...
2026-11-05 03:42:50,338 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.10/linear_attn/conv_out/Transpose ...
2026-11-05 03:42:50,338 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.10/linear_attn/split_qkv/Split ...
2026-11-05 03:42:50,338 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.10/linear_attn/q_l2norm/flat/Reshape ...
2026-11-05 03:42:50,338 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.10/linear_attn/q_l2norm/LpNormalization ...
2026-11-05 03:42:50,338 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.10/linear_attn/q_l2norm/unflat/Reshape ...
2026-11-05 03:42:50,338 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.10/linear_attn/k_l2norm/flat/Reshape ...
2026-11-05 03:42:50,338 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.10/linear_attn/k_l2norm/LpNormalization ...
2026-11-05 03:42:50,338 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.10/linear_attn/k_l2norm/unflat/Reshape ...
2026-11-05 03:42:50,338 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.10/linear_attn/q_scaled/Mul ...
2026-11-05 03:42:50,338 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.10/linear_attn/LinearAttentionGate ...
2026-11-05 03:42:50,338 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.10/linear_attn/LinearAttention ...
2026-11-05 03:42:50,338 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.10/linear_attn/GatedRMSNorm ...
2026-11-05 03:42:50,338 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.10/linear_attn/out_proj/MatMul ...
2026-11-05 03:42:50,360 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.10/linear_attn/out_proj/MatMul with 4 bits ...
2026-11-05 03:42:50,360 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.10/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:50,360 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.10/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:50,520 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.10/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:50,520 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.10/mlp/gate_up_proj/Split ...
2026-11-05 03:42:50,520 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.10/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:50,520 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.10/mlp/act_fn/Mul ...
2026-11-05 03:42:50,520 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.10/mlp/Mul ...
2026-11-05 03:42:50,520 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.10/mlp/down_proj/MatMul ...
2026-11-05 03:42:50,592 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.10/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:50,592 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.11/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:50,592 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.11/attn/qkv_proj/MatMul ...
2026-11-05 03:42:50,669 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.11/attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:50,669 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.11/attn/qkv_proj/Split ...
2026-11-05 03:42:50,669 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.11/attn/q_gate/Reshape ...
2026-11-05 03:42:50,669 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.11/attn/q_gate/Split ...
2026-11-05 03:42:50,669 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.11/attn/q_proj/Reshape ...
2026-11-05 03:42:50,669 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.11/attn/gate/Reshape ...
2026-11-05 03:42:50,669 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.11/attn/q_norm/Reshape_1 ...
2026-11-05 03:42:50,669 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.11/attn/q_norm/SimplifiedLayerNormalization ...
2026-11-05 03:42:50,669 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.11/attn/q_norm/Reshape_2 ...
2026-11-05 03:42:50,669 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.11/attn/k_norm/Reshape_1 ...
2026-11-05 03:42:50,669 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.11/attn/k_norm/SimplifiedLayerNormalization ...
2026-11-05 03:42:50,669 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.11/attn/k_norm/Reshape_2 ...
2026-11-05 03:42:50,669 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.11/attn/q_rotary/MRotaryEmbedding ...
2026-11-05 03:42:50,669 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.11/attn/k_rotary/MRotaryEmbedding ...
2026-11-05 03:42:50,669 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.11/attn/GroupQueryAttention ...
2026-11-05 03:42:50,669 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.11/attn/gate/Sigmoid ...
2026-11-05 03:42:50,669 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.11/attn/gate/Mul ...
2026-11-05 03:42:50,669 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.11/attn/o_proj/MatMul ...
2026-11-05 03:42:50,690 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.11/attn/o_proj/MatMul with 4 bits ...
2026-11-05 03:42:50,690 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.11/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:50,690 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.11/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:50,846 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.11/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:50,846 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.11/mlp/gate_up_proj/Split ...
2026-11-05 03:42:50,846 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.11/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:50,846 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.11/mlp/act_fn/Mul ...
2026-11-05 03:42:50,846 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.11/mlp/Mul ...
2026-11-05 03:42:50,846 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.11/mlp/down_proj/MatMul ...
2026-11-05 03:42:50,915 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.11/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:50,915 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.12/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:50,915 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.12/linear_attn/qkv_proj/MatMul ...
2026-11-05 03:42:50,976 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.12/linear_attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:50,976 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.12/linear_attn/z_proj/MatMul ...
2026-11-05 03:42:50,999 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.12/linear_attn/z_proj/MatMul with 4 bits ...
2026-11-05 03:42:50,999 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.12/linear_attn/b_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:50,999 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.12/linear_attn/a_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:50,999 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.12/linear_attn/qkv_proj/Transpose ...
2026-11-05 03:42:50,999 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.12/linear_attn/CausalConvWithState ...
2026-11-05 03:42:50,999 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.12/linear_attn/conv_out/Transpose ...
2026-11-05 03:42:50,999 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.12/linear_attn/split_qkv/Split ...
2026-11-05 03:42:50,999 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.12/linear_attn/q_l2norm/flat/Reshape ...
2026-11-05 03:42:50,999 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.12/linear_attn/q_l2norm/LpNormalization ...
2026-11-05 03:42:50,999 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.12/linear_attn/q_l2norm/unflat/Reshape ...
2026-11-05 03:42:50,999 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.12/linear_attn/k_l2norm/flat/Reshape ...
2026-11-05 03:42:50,999 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.12/linear_attn/k_l2norm/LpNormalization ...
2026-11-05 03:42:51,000 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.12/linear_attn/k_l2norm/unflat/Reshape ...
2026-11-05 03:42:51,000 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.12/linear_attn/q_scaled/Mul ...
2026-11-05 03:42:51,000 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.12/linear_attn/LinearAttentionGate ...
2026-11-05 03:42:51,000 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.12/linear_attn/LinearAttention ...
2026-11-05 03:42:51,000 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.12/linear_attn/GatedRMSNorm ...
2026-11-05 03:42:51,000 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.12/linear_attn/out_proj/MatMul ...
2026-11-05 03:42:51,022 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.12/linear_attn/out_proj/MatMul with 4 bits ...
2026-11-05 03:42:51,022 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.12/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:51,022 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.12/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:51,199 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.12/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:51,199 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.12/mlp/gate_up_proj/Split ...
2026-11-05 03:42:51,199 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.12/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:51,199 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.12/mlp/act_fn/Mul ...
2026-11-05 03:42:51,199 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.12/mlp/Mul ...
2026-11-05 03:42:51,199 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.12/mlp/down_proj/MatMul ...
2026-11-05 03:42:51,262 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.12/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:51,262 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.13/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:51,262 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.13/linear_attn/qkv_proj/MatMul ...
2026-11-05 03:42:51,314 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.13/linear_attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:51,314 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.13/linear_attn/z_proj/MatMul ...
2026-11-05 03:42:51,336 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.13/linear_attn/z_proj/MatMul with 4 bits ...
2026-11-05 03:42:51,336 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.13/linear_attn/b_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:51,336 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.13/linear_attn/a_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:51,336 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.13/linear_attn/qkv_proj/Transpose ...
2026-11-05 03:42:51,336 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.13/linear_attn/CausalConvWithState ...
2026-11-05 03:42:51,336 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.13/linear_attn/conv_out/Transpose ...
2026-11-05 03:42:51,336 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.13/linear_attn/split_qkv/Split ...
2026-11-05 03:42:51,336 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.13/linear_attn/q_l2norm/flat/Reshape ...
2026-11-05 03:42:51,336 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.13/linear_attn/q_l2norm/LpNormalization ...
2026-11-05 03:42:51,336 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.13/linear_attn/q_l2norm/unflat/Reshape ...
2026-11-05 03:42:51,336 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.13/linear_attn/k_l2norm/flat/Reshape ...
2026-11-05 03:42:51,336 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.13/linear_attn/k_l2norm/LpNormalization ...
2026-11-05 03:42:51,336 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.13/linear_attn/k_l2norm/unflat/Reshape ...
2026-11-05 03:42:51,336 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.13/linear_attn/q_scaled/Mul ...
2026-11-05 03:42:51,336 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.13/linear_attn/LinearAttentionGate ...
2026-11-05 03:42:51,336 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.13/linear_attn/LinearAttention ...
2026-11-05 03:42:51,336 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.13/linear_attn/GatedRMSNorm ...
2026-11-05 03:42:51,336 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.13/linear_attn/out_proj/MatMul ...
2026-11-05 03:42:51,363 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.13/linear_attn/out_proj/MatMul with 4 bits ...
2026-11-05 03:42:51,364 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.13/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:51,364 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.13/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:51,536 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.13/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:51,536 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.13/mlp/gate_up_proj/Split ...
2026-11-05 03:42:51,536 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.13/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:51,536 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.13/mlp/act_fn/Mul ...
2026-11-05 03:42:51,536 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.13/mlp/Mul ...
2026-11-05 03:42:51,536 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.13/mlp/down_proj/MatMul ...
2026-11-05 03:42:51,614 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.13/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:51,614 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.14/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:51,614 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.14/linear_attn/qkv_proj/MatMul ...
2026-11-05 03:42:51,664 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.14/linear_attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:51,664 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.14/linear_attn/z_proj/MatMul ...
2026-11-05 03:42:51,696 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.14/linear_attn/z_proj/MatMul with 4 bits ...
2026-11-05 03:42:51,696 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.14/linear_attn/b_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:51,696 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.14/linear_attn/a_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:51,696 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.14/linear_attn/qkv_proj/Transpose ...
2026-11-05 03:42:51,696 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.14/linear_attn/CausalConvWithState ...
2026-11-05 03:42:51,696 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.14/linear_attn/conv_out/Transpose ...
2026-11-05 03:42:51,696 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.14/linear_attn/split_qkv/Split ...
2026-11-05 03:42:51,696 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.14/linear_attn/q_l2norm/flat/Reshape ...
2026-11-05 03:42:51,696 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.14/linear_attn/q_l2norm/LpNormalization ...
2026-11-05 03:42:51,696 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.14/linear_attn/q_l2norm/unflat/Reshape ...
2026-11-05 03:42:51,696 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.14/linear_attn/k_l2norm/flat/Reshape ...
2026-11-05 03:42:51,696 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.14/linear_attn/k_l2norm/LpNormalization ...
2026-11-05 03:42:51,696 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.14/linear_attn/k_l2norm/unflat/Reshape ...
2026-11-05 03:42:51,696 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.14/linear_attn/q_scaled/Mul ...
2026-11-05 03:42:51,696 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.14/linear_attn/LinearAttentionGate ...
2026-11-05 03:42:51,696 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.14/linear_attn/LinearAttention ...
2026-11-05 03:42:51,696 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.14/linear_attn/GatedRMSNorm ...
2026-11-05 03:42:51,696 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.14/linear_attn/out_proj/MatMul ...
2026-11-05 03:42:51,731 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.14/linear_attn/out_proj/MatMul with 4 bits ...
2026-11-05 03:42:51,731 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.14/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:51,731 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.14/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:51,885 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.14/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:51,885 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.14/mlp/gate_up_proj/Split ...
2026-11-05 03:42:51,885 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.14/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:51,885 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.14/mlp/act_fn/Mul ...
2026-11-05 03:42:51,885 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.14/mlp/Mul ...
2026-11-05 03:42:51,885 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.14/mlp/down_proj/MatMul ...
2026-11-05 03:42:51,947 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.14/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:51,947 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.15/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:51,947 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.15/attn/qkv_proj/MatMul ...
2026-11-05 03:42:52,009 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.15/attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:52,009 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.15/attn/qkv_proj/Split ...
2026-11-05 03:42:52,009 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.15/attn/q_gate/Reshape ...
2026-11-05 03:42:52,009 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.15/attn/q_gate/Split ...
2026-11-05 03:42:52,009 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.15/attn/q_proj/Reshape ...
2026-11-05 03:42:52,009 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.15/attn/gate/Reshape ...
2026-11-05 03:42:52,009 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.15/attn/q_norm/Reshape_1 ...
2026-11-05 03:42:52,009 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.15/attn/q_norm/SimplifiedLayerNormalization ...
2026-11-05 03:42:52,009 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.15/attn/q_norm/Reshape_2 ...
2026-11-05 03:42:52,009 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.15/attn/k_norm/Reshape_1 ...
2026-11-05 03:42:52,009 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.15/attn/k_norm/SimplifiedLayerNormalization ...
2026-11-05 03:42:52,009 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.15/attn/k_norm/Reshape_2 ...
2026-11-05 03:42:52,009 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.15/attn/q_rotary/MRotaryEmbedding ...
2026-11-05 03:42:52,009 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.15/attn/k_rotary/MRotaryEmbedding ...
2026-11-05 03:42:52,009 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.15/attn/GroupQueryAttention ...
2026-11-05 03:42:52,009 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.15/attn/gate/Sigmoid ...
2026-11-05 03:42:52,009 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.15/attn/gate/Mul ...
2026-11-05 03:42:52,009 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.15/attn/o_proj/MatMul ...
2026-11-05 03:42:52,032 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.15/attn/o_proj/MatMul with 4 bits ...
2026-11-05 03:42:52,032 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.15/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:52,032 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.15/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:52,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.15/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:52,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.15/mlp/gate_up_proj/Split ...
2026-11-05 03:42:52,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.15/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:52,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.15/mlp/act_fn/Mul ...
2026-11-05 03:42:52,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.15/mlp/Mul ...
2026-11-05 03:42:52,194 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.15/mlp/down_proj/MatMul ...
2026-11-05 03:42:52,264 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.15/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:52,264 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.16/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:52,264 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.16/linear_attn/qkv_proj/MatMul ...
2026-11-05 03:42:52,308 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.16/linear_attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:52,308 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.16/linear_attn/z_proj/MatMul ...
2026-11-05 03:42:52,331 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.16/linear_attn/z_proj/MatMul with 4 bits ...
2026-11-05 03:42:52,331 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.16/linear_attn/b_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:52,331 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.16/linear_attn/a_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:52,331 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.16/linear_attn/qkv_proj/Transpose ...
2026-11-05 03:42:52,331 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.16/linear_attn/CausalConvWithState ...
2026-11-05 03:42:52,331 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.16/linear_attn/conv_out/Transpose ...
2026-11-05 03:42:52,331 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.16/linear_attn/split_qkv/Split ...
2026-11-05 03:42:52,331 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.16/linear_attn/q_l2norm/flat/Reshape ...
2026-11-05 03:42:52,331 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.16/linear_attn/q_l2norm/LpNormalization ...
2026-11-05 03:42:52,331 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.16/linear_attn/q_l2norm/unflat/Reshape ...
2026-11-05 03:42:52,331 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.16/linear_attn/k_l2norm/flat/Reshape ...
2026-11-05 03:42:52,331 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.16/linear_attn/k_l2norm/LpNormalization ...
2026-11-05 03:42:52,331 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.16/linear_attn/k_l2norm/unflat/Reshape ...
2026-11-05 03:42:52,331 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.16/linear_attn/q_scaled/Mul ...
2026-11-05 03:42:52,331 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.16/linear_attn/LinearAttentionGate ...
2026-11-05 03:42:52,331 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.16/linear_attn/LinearAttention ...
2026-11-05 03:42:52,331 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.16/linear_attn/GatedRMSNorm ...
2026-11-05 03:42:52,331 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.16/linear_attn/out_proj/MatMul ...
2026-11-05 03:42:52,352 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.16/linear_attn/out_proj/MatMul with 4 bits ...
2026-11-05 03:42:52,352 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.16/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:52,352 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.16/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:52,506 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.16/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:52,506 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.16/mlp/gate_up_proj/Split ...
2026-11-05 03:42:52,506 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.16/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:52,506 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.16/mlp/act_fn/Mul ...
2026-11-05 03:42:52,506 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.16/mlp/Mul ...
2026-11-05 03:42:52,506 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.16/mlp/down_proj/MatMul ...
2026-11-05 03:42:52,573 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.16/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:52,573 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.17/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:52,573 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.17/linear_attn/qkv_proj/MatMul ...
2026-11-05 03:42:52,620 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.17/linear_attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:52,621 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.17/linear_attn/z_proj/MatMul ...
2026-11-05 03:42:52,642 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.17/linear_attn/z_proj/MatMul with 4 bits ...
2026-11-05 03:42:52,643 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.17/linear_attn/b_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:52,643 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.17/linear_attn/a_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:52,643 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.17/linear_attn/qkv_proj/Transpose ...
2026-11-05 03:42:52,643 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.17/linear_attn/CausalConvWithState ...
2026-11-05 03:42:52,643 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.17/linear_attn/conv_out/Transpose ...
2026-11-05 03:42:52,643 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.17/linear_attn/split_qkv/Split ...
2026-11-05 03:42:52,643 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.17/linear_attn/q_l2norm/flat/Reshape ...
2026-11-05 03:42:52,643 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.17/linear_attn/q_l2norm/LpNormalization ...
2026-11-05 03:42:52,643 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.17/linear_attn/q_l2norm/unflat/Reshape ...
2026-11-05 03:42:52,643 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.17/linear_attn/k_l2norm/flat/Reshape ...
2026-11-05 03:42:52,643 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.17/linear_attn/k_l2norm/LpNormalization ...
2026-11-05 03:42:52,643 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.17/linear_attn/k_l2norm/unflat/Reshape ...
2026-11-05 03:42:52,643 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.17/linear_attn/q_scaled/Mul ...
2026-11-05 03:42:52,643 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.17/linear_attn/LinearAttentionGate ...
2026-11-05 03:42:52,643 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.17/linear_attn/LinearAttention ...
2026-11-05 03:42:52,643 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.17/linear_attn/GatedRMSNorm ...
2026-11-05 03:42:52,643 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.17/linear_attn/out_proj/MatMul ...
2026-11-05 03:42:52,664 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.17/linear_attn/out_proj/MatMul with 4 bits ...
2026-11-05 03:42:52,664 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.17/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:52,664 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.17/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:52,813 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.17/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:52,813 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.17/mlp/gate_up_proj/Split ...
2026-11-05 03:42:52,813 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.17/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:52,813 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.17/mlp/act_fn/Mul ...
2026-11-05 03:42:52,813 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.17/mlp/Mul ...
2026-11-05 03:42:52,813 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.17/mlp/down_proj/MatMul ...
2026-11-05 03:42:52,862 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.17/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:52,863 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.18/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:52,863 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.18/linear_attn/qkv_proj/MatMul ...
2026-11-05 03:42:52,907 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.18/linear_attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:52,907 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.18/linear_attn/z_proj/MatMul ...
2026-11-05 03:42:52,921 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.18/linear_attn/z_proj/MatMul with 4 bits ...
2026-11-05 03:42:52,921 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.18/linear_attn/b_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:52,921 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.18/linear_attn/a_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:52,921 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.18/linear_attn/qkv_proj/Transpose ...
2026-11-05 03:42:52,921 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.18/linear_attn/CausalConvWithState ...
2026-11-05 03:42:52,921 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.18/linear_attn/conv_out/Transpose ...
2026-11-05 03:42:52,921 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.18/linear_attn/split_qkv/Split ...
2026-11-05 03:42:52,921 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.18/linear_attn/q_l2norm/flat/Reshape ...
2026-11-05 03:42:52,921 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.18/linear_attn/q_l2norm/LpNormalization ...
2026-11-05 03:42:52,921 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.18/linear_attn/q_l2norm/unflat/Reshape ...
2026-11-05 03:42:52,921 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.18/linear_attn/k_l2norm/flat/Reshape ...
2026-11-05 03:42:52,921 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.18/linear_attn/k_l2norm/LpNormalization ...
2026-11-05 03:42:52,921 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.18/linear_attn/k_l2norm/unflat/Reshape ...
2026-11-05 03:42:52,921 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.18/linear_attn/q_scaled/Mul ...
2026-11-05 03:42:52,921 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.18/linear_attn/LinearAttentionGate ...
2026-11-05 03:42:52,921 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.18/linear_attn/LinearAttention ...
2026-11-05 03:42:52,921 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.18/linear_attn/GatedRMSNorm ...
2026-11-05 03:42:52,921 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.18/linear_attn/out_proj/MatMul ...
2026-11-05 03:42:52,937 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.18/linear_attn/out_proj/MatMul with 4 bits ...
2026-11-05 03:42:52,937 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.18/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:52,937 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.18/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:53,091 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.18/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:53,091 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.18/mlp/gate_up_proj/Split ...
2026-11-05 03:42:53,091 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.18/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:53,091 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.18/mlp/act_fn/Mul ...
2026-11-05 03:42:53,091 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.18/mlp/Mul ...
2026-11-05 03:42:53,091 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.18/mlp/down_proj/MatMul ...
2026-11-05 03:42:53,143 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.18/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:53,143 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.19/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:53,143 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.19/attn/qkv_proj/MatMul ...
2026-11-05 03:42:53,203 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.19/attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:53,203 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.19/attn/qkv_proj/Split ...
2026-11-05 03:42:53,203 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.19/attn/q_gate/Reshape ...
2026-11-05 03:42:53,203 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.19/attn/q_gate/Split ...
2026-11-05 03:42:53,203 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.19/attn/q_proj/Reshape ...
2026-11-05 03:42:53,203 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.19/attn/gate/Reshape ...
2026-11-05 03:42:53,203 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.19/attn/q_norm/Reshape_1 ...
2026-11-05 03:42:53,203 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.19/attn/q_norm/SimplifiedLayerNormalization ...
2026-11-05 03:42:53,203 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.19/attn/q_norm/Reshape_2 ...
2026-11-05 03:42:53,203 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.19/attn/k_norm/Reshape_1 ...
2026-11-05 03:42:53,203 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.19/attn/k_norm/SimplifiedLayerNormalization ...
2026-11-05 03:42:53,203 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.19/attn/k_norm/Reshape_2 ...
2026-11-05 03:42:53,203 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.19/attn/q_rotary/MRotaryEmbedding ...
2026-11-05 03:42:53,203 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.19/attn/k_rotary/MRotaryEmbedding ...
2026-11-05 03:42:53,203 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.19/attn/GroupQueryAttention ...
2026-11-05 03:42:53,203 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.19/attn/gate/Sigmoid ...
2026-11-05 03:42:53,203 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.19/attn/gate/Mul ...
2026-11-05 03:42:53,203 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.19/attn/o_proj/MatMul ...
2026-11-05 03:42:53,227 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.19/attn/o_proj/MatMul with 4 bits ...
2026-11-05 03:42:53,227 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.19/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:53,227 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.19/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:53,371 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.19/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:53,371 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.19/mlp/gate_up_proj/Split ...
2026-11-05 03:42:53,371 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.19/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:53,372 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.19/mlp/act_fn/Mul ...
2026-11-05 03:42:53,372 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.19/mlp/Mul ...
2026-11-05 03:42:53,372 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.19/mlp/down_proj/MatMul ...
2026-11-05 03:42:53,458 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.19/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:53,459 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.20/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:53,459 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.20/linear_attn/qkv_proj/MatMul ...
2026-11-05 03:42:53,503 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.20/linear_attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:53,503 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.20/linear_attn/z_proj/MatMul ...
2026-11-05 03:42:53,526 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.20/linear_attn/z_proj/MatMul with 4 bits ...
2026-11-05 03:42:53,526 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.20/linear_attn/b_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:53,526 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.20/linear_attn/a_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:53,526 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.20/linear_attn/qkv_proj/Transpose ...
2026-11-05 03:42:53,526 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.20/linear_attn/CausalConvWithState ...
2026-11-05 03:42:53,526 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.20/linear_attn/conv_out/Transpose ...
2026-11-05 03:42:53,526 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.20/linear_attn/split_qkv/Split ...
2026-11-05 03:42:53,526 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.20/linear_attn/q_l2norm/flat/Reshape ...
2026-11-05 03:42:53,526 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.20/linear_attn/q_l2norm/LpNormalization ...
2026-11-05 03:42:53,526 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.20/linear_attn/q_l2norm/unflat/Reshape ...
2026-11-05 03:42:53,526 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.20/linear_attn/k_l2norm/flat/Reshape ...
2026-11-05 03:42:53,526 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.20/linear_attn/k_l2norm/LpNormalization ...
2026-11-05 03:42:53,526 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.20/linear_attn/k_l2norm/unflat/Reshape ...
2026-11-05 03:42:53,526 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.20/linear_attn/q_scaled/Mul ...
2026-11-05 03:42:53,526 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.20/linear_attn/LinearAttentionGate ...
2026-11-05 03:42:53,526 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.20/linear_attn/LinearAttention ...
2026-11-05 03:42:53,526 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.20/linear_attn/GatedRMSNorm ...
2026-11-05 03:42:53,526 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.20/linear_attn/out_proj/MatMul ...
2026-11-05 03:42:53,561 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.20/linear_attn/out_proj/MatMul with 4 bits ...
2026-11-05 03:42:53,561 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.20/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:53,561 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.20/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:53,704 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.20/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:53,704 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.20/mlp/gate_up_proj/Split ...
2026-11-05 03:42:53,704 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.20/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:53,704 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.20/mlp/act_fn/Mul ...
2026-11-05 03:42:53,704 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.20/mlp/Mul ...
2026-11-05 03:42:53,704 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.20/mlp/down_proj/MatMul ...
2026-11-05 03:42:53,754 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.20/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:53,754 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.21/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:53,754 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.21/linear_attn/qkv_proj/MatMul ...
2026-11-05 03:42:53,808 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.21/linear_attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:53,808 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.21/linear_attn/z_proj/MatMul ...
2026-11-05 03:42:53,830 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.21/linear_attn/z_proj/MatMul with 4 bits ...
2026-11-05 03:42:53,830 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.21/linear_attn/b_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:53,830 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.21/linear_attn/a_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:53,830 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.21/linear_attn/qkv_proj/Transpose ...
2026-11-05 03:42:53,830 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.21/linear_attn/CausalConvWithState ...
2026-11-05 03:42:53,830 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.21/linear_attn/conv_out/Transpose ...
2026-11-05 03:42:53,830 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.21/linear_attn/split_qkv/Split ...
2026-11-05 03:42:53,830 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.21/linear_attn/q_l2norm/flat/Reshape ...
2026-11-05 03:42:53,830 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.21/linear_attn/q_l2norm/LpNormalization ...
2026-11-05 03:42:53,830 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.21/linear_attn/q_l2norm/unflat/Reshape ...
2026-11-05 03:42:53,830 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.21/linear_attn/k_l2norm/flat/Reshape ...
2026-11-05 03:42:53,830 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.21/linear_attn/k_l2norm/LpNormalization ...
2026-11-05 03:42:53,830 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.21/linear_attn/k_l2norm/unflat/Reshape ...
2026-11-05 03:42:53,830 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.21/linear_attn/q_scaled/Mul ...
2026-11-05 03:42:53,830 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.21/linear_attn/LinearAttentionGate ...
2026-11-05 03:42:53,830 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.21/linear_attn/LinearAttention ...
2026-11-05 03:42:53,830 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.21/linear_attn/GatedRMSNorm ...
2026-11-05 03:42:53,830 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.21/linear_attn/out_proj/MatMul ...
2026-11-05 03:42:53,853 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.21/linear_attn/out_proj/MatMul with 4 bits ...
2026-11-05 03:42:53,853 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.21/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:53,853 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.21/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:54,013 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.21/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:54,013 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.21/mlp/gate_up_proj/Split ...
2026-11-05 03:42:54,013 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.21/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:54,013 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.21/mlp/act_fn/Mul ...
2026-11-05 03:42:54,013 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.21/mlp/Mul ...
2026-11-05 03:42:54,013 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.21/mlp/down_proj/MatMul ...
2026-11-05 03:42:54,066 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.21/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:54,066 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.22/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:54,066 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.22/linear_attn/qkv_proj/MatMul ...
2026-11-05 03:42:54,108 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.22/linear_attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:54,108 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.22/linear_attn/z_proj/MatMul ...
2026-11-05 03:42:54,131 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.22/linear_attn/z_proj/MatMul with 4 bits ...
2026-11-05 03:42:54,131 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.22/linear_attn/b_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:54,131 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.22/linear_attn/a_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:54,131 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.22/linear_attn/qkv_proj/Transpose ...
2026-11-05 03:42:54,131 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.22/linear_attn/CausalConvWithState ...
2026-11-05 03:42:54,131 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.22/linear_attn/conv_out/Transpose ...
2026-11-05 03:42:54,131 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.22/linear_attn/split_qkv/Split ...
2026-11-05 03:42:54,131 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.22/linear_attn/q_l2norm/flat/Reshape ...
2026-11-05 03:42:54,131 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.22/linear_attn/q_l2norm/LpNormalization ...
2026-11-05 03:42:54,131 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.22/linear_attn/q_l2norm/unflat/Reshape ...
2026-11-05 03:42:54,131 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.22/linear_attn/k_l2norm/flat/Reshape ...
2026-11-05 03:42:54,131 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.22/linear_attn/k_l2norm/LpNormalization ...
2026-11-05 03:42:54,131 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.22/linear_attn/k_l2norm/unflat/Reshape ...
2026-11-05 03:42:54,131 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.22/linear_attn/q_scaled/Mul ...
2026-11-05 03:42:54,131 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.22/linear_attn/LinearAttentionGate ...
2026-11-05 03:42:54,131 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.22/linear_attn/LinearAttention ...
2026-11-05 03:42:54,131 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.22/linear_attn/GatedRMSNorm ...
2026-11-05 03:42:54,131 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.22/linear_attn/out_proj/MatMul ...
2026-11-05 03:42:54,154 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.22/linear_attn/out_proj/MatMul with 4 bits ...
2026-11-05 03:42:54,154 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.22/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:54,154 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.22/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:54,283 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.22/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:54,283 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.22/mlp/gate_up_proj/Split ...
2026-11-05 03:42:54,283 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.22/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:54,283 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.22/mlp/act_fn/Mul ...
2026-11-05 03:42:54,283 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.22/mlp/Mul ...
2026-11-05 03:42:54,283 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.22/mlp/down_proj/MatMul ...
2026-11-05 03:42:54,326 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.22/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:54,326 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.23/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:54,326 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.23/attn/qkv_proj/MatMul ...
2026-11-05 03:42:54,383 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.23/attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:54,383 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.23/attn/qkv_proj/Split ...
2026-11-05 03:42:54,383 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.23/attn/q_gate/Reshape ...
2026-11-05 03:42:54,383 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.23/attn/q_gate/Split ...
2026-11-05 03:42:54,383 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.23/attn/q_proj/Reshape ...
2026-11-05 03:42:54,383 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.23/attn/gate/Reshape ...
2026-11-05 03:42:54,383 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.23/attn/q_norm/Reshape_1 ...
2026-11-05 03:42:54,383 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.23/attn/q_norm/SimplifiedLayerNormalization ...
2026-11-05 03:42:54,383 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.23/attn/q_norm/Reshape_2 ...
2026-11-05 03:42:54,383 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.23/attn/k_norm/Reshape_1 ...
2026-11-05 03:42:54,383 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.23/attn/k_norm/SimplifiedLayerNormalization ...
2026-11-05 03:42:54,383 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.23/attn/k_norm/Reshape_2 ...
2026-11-05 03:42:54,383 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.23/attn/q_rotary/MRotaryEmbedding ...
2026-11-05 03:42:54,383 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.23/attn/k_rotary/MRotaryEmbedding ...
2026-11-05 03:42:54,383 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.23/attn/GroupQueryAttention ...
2026-11-05 03:42:54,383 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.23/attn/gate/Sigmoid ...
2026-11-05 03:42:54,383 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.23/attn/gate/Mul ...
2026-11-05 03:42:54,383 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.23/attn/o_proj/MatMul ...
2026-11-05 03:42:54,397 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.23/attn/o_proj/MatMul with 4 bits ...
2026-11-05 03:42:54,397 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.23/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:54,397 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.23/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:54,524 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.23/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:54,524 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.23/mlp/gate_up_proj/Split ...
2026-11-05 03:42:54,524 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.23/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:54,524 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.23/mlp/act_fn/Mul ...
2026-11-05 03:42:54,524 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.23/mlp/Mul ...
2026-11-05 03:42:54,524 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.23/mlp/down_proj/MatMul ...
2026-11-05 03:42:54,568 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.23/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:54,568 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.24/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:54,568 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.24/linear_attn/qkv_proj/MatMul ...
2026-11-05 03:42:54,617 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.24/linear_attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:54,617 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.24/linear_attn/z_proj/MatMul ...
2026-11-05 03:42:54,639 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.24/linear_attn/z_proj/MatMul with 4 bits ...
2026-11-05 03:42:54,639 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.24/linear_attn/b_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:54,639 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.24/linear_attn/a_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:54,639 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.24/linear_attn/qkv_proj/Transpose ...
2026-11-05 03:42:54,639 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.24/linear_attn/CausalConvWithState ...
2026-11-05 03:42:54,639 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.24/linear_attn/conv_out/Transpose ...
2026-11-05 03:42:54,639 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.24/linear_attn/split_qkv/Split ...
2026-11-05 03:42:54,639 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.24/linear_attn/q_l2norm/flat/Reshape ...
2026-11-05 03:42:54,640 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.24/linear_attn/q_l2norm/LpNormalization ...
2026-11-05 03:42:54,640 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.24/linear_attn/q_l2norm/unflat/Reshape ...
2026-11-05 03:42:54,640 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.24/linear_attn/k_l2norm/flat/Reshape ...
2026-11-05 03:42:54,640 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.24/linear_attn/k_l2norm/LpNormalization ...
2026-11-05 03:42:54,640 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.24/linear_attn/k_l2norm/unflat/Reshape ...
2026-11-05 03:42:54,640 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.24/linear_attn/q_scaled/Mul ...
2026-11-05 03:42:54,640 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.24/linear_attn/LinearAttentionGate ...
2026-11-05 03:42:54,640 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.24/linear_attn/LinearAttention ...
2026-11-05 03:42:54,640 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.24/linear_attn/GatedRMSNorm ...
2026-11-05 03:42:54,640 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.24/linear_attn/out_proj/MatMul ...
2026-11-05 03:42:54,661 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.24/linear_attn/out_proj/MatMul with 4 bits ...
2026-11-05 03:42:54,661 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.24/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:54,661 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.24/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:54,802 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.24/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:54,802 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.24/mlp/gate_up_proj/Split ...
2026-11-05 03:42:54,802 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.24/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:54,802 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.24/mlp/act_fn/Mul ...
2026-11-05 03:42:54,802 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.24/mlp/Mul ...
2026-11-05 03:42:54,802 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.24/mlp/down_proj/MatMul ...
2026-11-05 03:42:54,852 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.24/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:54,852 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.25/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:54,852 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.25/linear_attn/qkv_proj/MatMul ...
2026-11-05 03:42:54,896 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.25/linear_attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:54,896 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.25/linear_attn/z_proj/MatMul ...
2026-11-05 03:42:54,916 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.25/linear_attn/z_proj/MatMul with 4 bits ...
2026-11-05 03:42:54,916 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.25/linear_attn/b_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:54,916 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.25/linear_attn/a_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:54,916 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.25/linear_attn/qkv_proj/Transpose ...
2026-11-05 03:42:54,916 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.25/linear_attn/CausalConvWithState ...
2026-11-05 03:42:54,916 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.25/linear_attn/conv_out/Transpose ...
2026-11-05 03:42:54,916 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.25/linear_attn/split_qkv/Split ...
2026-11-05 03:42:54,916 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.25/linear_attn/q_l2norm/flat/Reshape ...
2026-11-05 03:42:54,916 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.25/linear_attn/q_l2norm/LpNormalization ...
2026-11-05 03:42:54,916 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.25/linear_attn/q_l2norm/unflat/Reshape ...
2026-11-05 03:42:54,916 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.25/linear_attn/k_l2norm/flat/Reshape ...
2026-11-05 03:42:54,916 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.25/linear_attn/k_l2norm/LpNormalization ...
2026-11-05 03:42:54,916 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.25/linear_attn/k_l2norm/unflat/Reshape ...
2026-11-05 03:42:54,916 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.25/linear_attn/q_scaled/Mul ...
2026-11-05 03:42:54,916 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.25/linear_attn/LinearAttentionGate ...
2026-11-05 03:42:54,916 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.25/linear_attn/LinearAttention ...
2026-11-05 03:42:54,916 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.25/linear_attn/GatedRMSNorm ...
2026-11-05 03:42:54,916 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.25/linear_attn/out_proj/MatMul ...
2026-11-05 03:42:54,938 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.25/linear_attn/out_proj/MatMul with 4 bits ...
2026-11-05 03:42:54,938 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.25/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:54,938 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.25/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:55,086 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.25/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:55,086 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.25/mlp/gate_up_proj/Split ...
2026-11-05 03:42:55,086 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.25/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:55,086 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.25/mlp/act_fn/Mul ...
2026-11-05 03:42:55,086 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.25/mlp/Mul ...
2026-11-05 03:42:55,086 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.25/mlp/down_proj/MatMul ...
2026-11-05 03:42:55,140 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.25/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:55,140 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.26/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:55,140 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.26/linear_attn/qkv_proj/MatMul ...
2026-11-05 03:42:55,190 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.26/linear_attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:55,190 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.26/linear_attn/z_proj/MatMul ...
2026-11-05 03:42:55,212 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.26/linear_attn/z_proj/MatMul with 4 bits ...
2026-11-05 03:42:55,212 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.26/linear_attn/b_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:55,212 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.26/linear_attn/a_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:55,212 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.26/linear_attn/qkv_proj/Transpose ...
2026-11-05 03:42:55,212 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.26/linear_attn/CausalConvWithState ...
2026-11-05 03:42:55,212 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.26/linear_attn/conv_out/Transpose ...
2026-11-05 03:42:55,212 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.26/linear_attn/split_qkv/Split ...
2026-11-05 03:42:55,212 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.26/linear_attn/q_l2norm/flat/Reshape ...
2026-11-05 03:42:55,212 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.26/linear_attn/q_l2norm/LpNormalization ...
2026-11-05 03:42:55,212 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.26/linear_attn/q_l2norm/unflat/Reshape ...
2026-11-05 03:42:55,212 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.26/linear_attn/k_l2norm/flat/Reshape ...
2026-11-05 03:42:55,212 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.26/linear_attn/k_l2norm/LpNormalization ...
2026-11-05 03:42:55,212 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.26/linear_attn/k_l2norm/unflat/Reshape ...
2026-11-05 03:42:55,212 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.26/linear_attn/q_scaled/Mul ...
2026-11-05 03:42:55,212 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.26/linear_attn/LinearAttentionGate ...
2026-11-05 03:42:55,212 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.26/linear_attn/LinearAttention ...
2026-11-05 03:42:55,212 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.26/linear_attn/GatedRMSNorm ...
2026-11-05 03:42:55,212 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.26/linear_attn/out_proj/MatMul ...
2026-11-05 03:42:55,234 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.26/linear_attn/out_proj/MatMul with 4 bits ...
2026-11-05 03:42:55,234 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.26/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:55,234 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.26/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:55,377 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.26/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:55,377 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.26/mlp/gate_up_proj/Split ...
2026-11-05 03:42:55,377 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.26/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:55,377 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.26/mlp/act_fn/Mul ...
2026-11-05 03:42:55,377 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.26/mlp/Mul ...
2026-11-05 03:42:55,377 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.26/mlp/down_proj/MatMul ...
2026-11-05 03:42:55,422 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.26/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:55,422 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.27/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:55,422 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.27/attn/qkv_proj/MatMul ...
2026-11-05 03:42:55,481 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.27/attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:55,482 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.27/attn/qkv_proj/Split ...
2026-11-05 03:42:55,482 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.27/attn/q_gate/Reshape ...
2026-11-05 03:42:55,482 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.27/attn/q_gate/Split ...
2026-11-05 03:42:55,482 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.27/attn/q_proj/Reshape ...
2026-11-05 03:42:55,482 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.27/attn/gate/Reshape ...
2026-11-05 03:42:55,482 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.27/attn/q_norm/Reshape_1 ...
2026-11-05 03:42:55,482 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.27/attn/q_norm/SimplifiedLayerNormalization ...
2026-11-05 03:42:55,482 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.27/attn/q_norm/Reshape_2 ...
2026-11-05 03:42:55,482 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.27/attn/k_norm/Reshape_1 ...
2026-11-05 03:42:55,482 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.27/attn/k_norm/SimplifiedLayerNormalization ...
2026-11-05 03:42:55,482 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.27/attn/k_norm/Reshape_2 ...
2026-11-05 03:42:55,482 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.27/attn/q_rotary/MRotaryEmbedding ...
2026-11-05 03:42:55,482 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.27/attn/k_rotary/MRotaryEmbedding ...
2026-11-05 03:42:55,482 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.27/attn/GroupQueryAttention ...
2026-11-05 03:42:55,482 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.27/attn/gate/Sigmoid ...
2026-11-05 03:42:55,482 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.27/attn/gate/Mul ...
2026-11-05 03:42:55,482 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.27/attn/o_proj/MatMul ...
2026-11-05 03:42:55,505 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.27/attn/o_proj/MatMul with 4 bits ...
2026-11-05 03:42:55,505 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.27/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:55,505 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.27/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:55,645 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.27/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:55,646 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.27/mlp/gate_up_proj/Split ...
2026-11-05 03:42:55,646 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.27/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:55,646 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.27/mlp/act_fn/Mul ...
2026-11-05 03:42:55,646 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.27/mlp/Mul ...
2026-11-05 03:42:55,646 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.27/mlp/down_proj/MatMul ...
2026-11-05 03:42:55,691 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.27/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:55,691 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.28/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:55,691 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.28/linear_attn/qkv_proj/MatMul ...
2026-11-05 03:42:55,748 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.28/linear_attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:55,748 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.28/linear_attn/z_proj/MatMul ...
2026-11-05 03:42:55,775 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.28/linear_attn/z_proj/MatMul with 4 bits ...
2026-11-05 03:42:55,775 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.28/linear_attn/b_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:55,775 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.28/linear_attn/a_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:55,775 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.28/linear_attn/qkv_proj/Transpose ...
2026-11-05 03:42:55,775 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.28/linear_attn/CausalConvWithState ...
2026-11-05 03:42:55,775 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.28/linear_attn/conv_out/Transpose ...
2026-11-05 03:42:55,775 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.28/linear_attn/split_qkv/Split ...
2026-11-05 03:42:55,775 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.28/linear_attn/q_l2norm/flat/Reshape ...
2026-11-05 03:42:55,775 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.28/linear_attn/q_l2norm/LpNormalization ...
2026-11-05 03:42:55,775 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.28/linear_attn/q_l2norm/unflat/Reshape ...
2026-11-05 03:42:55,775 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.28/linear_attn/k_l2norm/flat/Reshape ...
2026-11-05 03:42:55,775 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.28/linear_attn/k_l2norm/LpNormalization ...
2026-11-05 03:42:55,775 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.28/linear_attn/k_l2norm/unflat/Reshape ...
2026-11-05 03:42:55,775 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.28/linear_attn/q_scaled/Mul ...
2026-11-05 03:42:55,775 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.28/linear_attn/LinearAttentionGate ...
2026-11-05 03:42:55,775 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.28/linear_attn/LinearAttention ...
2026-11-05 03:42:55,775 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.28/linear_attn/GatedRMSNorm ...
2026-11-05 03:42:55,775 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.28/linear_attn/out_proj/MatMul ...
2026-11-05 03:42:55,792 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.28/linear_attn/out_proj/MatMul with 4 bits ...
2026-11-05 03:42:55,792 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.28/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:55,792 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.28/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:55,946 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.28/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:55,946 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.28/mlp/gate_up_proj/Split ...
2026-11-05 03:42:55,946 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.28/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:55,946 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.28/mlp/act_fn/Mul ...
2026-11-05 03:42:55,946 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.28/mlp/Mul ...
2026-11-05 03:42:55,946 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.28/mlp/down_proj/MatMul ...
2026-11-05 03:42:55,999 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.28/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:55,999 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.29/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:55,999 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.29/linear_attn/qkv_proj/MatMul ...
2026-11-05 03:42:56,048 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.29/linear_attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:56,048 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.29/linear_attn/z_proj/MatMul ...
2026-11-05 03:42:56,063 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.29/linear_attn/z_proj/MatMul with 4 bits ...
2026-11-05 03:42:56,064 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.29/linear_attn/b_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:56,064 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.29/linear_attn/a_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:56,064 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.29/linear_attn/qkv_proj/Transpose ...
2026-11-05 03:42:56,064 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.29/linear_attn/CausalConvWithState ...
2026-11-05 03:42:56,064 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.29/linear_attn/conv_out/Transpose ...
2026-11-05 03:42:56,064 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.29/linear_attn/split_qkv/Split ...
2026-11-05 03:42:56,064 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.29/linear_attn/q_l2norm/flat/Reshape ...
2026-11-05 03:42:56,064 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.29/linear_attn/q_l2norm/LpNormalization ...
2026-11-05 03:42:56,064 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.29/linear_attn/q_l2norm/unflat/Reshape ...
2026-11-05 03:42:56,064 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.29/linear_attn/k_l2norm/flat/Reshape ...
2026-11-05 03:42:56,064 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.29/linear_attn/k_l2norm/LpNormalization ...
2026-11-05 03:42:56,064 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.29/linear_attn/k_l2norm/unflat/Reshape ...
2026-11-05 03:42:56,064 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.29/linear_attn/q_scaled/Mul ...
2026-11-05 03:42:56,064 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.29/linear_attn/LinearAttentionGate ...
2026-11-05 03:42:56,064 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.29/linear_attn/LinearAttention ...
2026-11-05 03:42:56,064 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.29/linear_attn/GatedRMSNorm ...
2026-11-05 03:42:56,064 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.29/linear_attn/out_proj/MatMul ...
2026-11-05 03:42:56,080 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.29/linear_attn/out_proj/MatMul with 4 bits ...
2026-11-05 03:42:56,080 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.29/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:56,080 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.29/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:56,243 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.29/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:56,243 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.29/mlp/gate_up_proj/Split ...
2026-11-05 03:42:56,243 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.29/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:56,243 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.29/mlp/act_fn/Mul ...
2026-11-05 03:42:56,243 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.29/mlp/Mul ...
2026-11-05 03:42:56,243 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.29/mlp/down_proj/MatMul ...
2026-11-05 03:42:56,356 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.29/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:56,356 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.30/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:56,357 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.30/linear_attn/qkv_proj/MatMul ...
2026-11-05 03:42:56,404 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.30/linear_attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:56,404 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.30/linear_attn/z_proj/MatMul ...
2026-11-05 03:42:56,426 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.30/linear_attn/z_proj/MatMul with 4 bits ...
2026-11-05 03:42:56,426 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.30/linear_attn/b_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:56,426 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - exclude to quantize /model/layers.30/linear_attn/a_proj/MatMul as specified by nodes_to_exclude...
2026-11-05 03:42:56,426 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.30/linear_attn/qkv_proj/Transpose ...
2026-11-05 03:42:56,426 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.30/linear_attn/CausalConvWithState ...
2026-11-05 03:42:56,426 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.30/linear_attn/conv_out/Transpose ...
2026-11-05 03:42:56,426 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.30/linear_attn/split_qkv/Split ...
2026-11-05 03:42:56,426 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.30/linear_attn/q_l2norm/flat/Reshape ...
2026-11-05 03:42:56,426 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.30/linear_attn/q_l2norm/LpNormalization ...
2026-11-05 03:42:56,426 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.30/linear_attn/q_l2norm/unflat/Reshape ...
2026-11-05 03:42:56,426 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.30/linear_attn/k_l2norm/flat/Reshape ...
2026-11-05 03:42:56,426 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.30/linear_attn/k_l2norm/LpNormalization ...
2026-11-05 03:42:56,426 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.30/linear_attn/k_l2norm/unflat/Reshape ...
2026-11-05 03:42:56,426 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.30/linear_attn/q_scaled/Mul ...
2026-11-05 03:42:56,426 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.30/linear_attn/LinearAttentionGate ...
2026-11-05 03:42:56,426 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.30/linear_attn/LinearAttention ...
2026-11-05 03:42:56,426 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.30/linear_attn/GatedRMSNorm ...
2026-11-05 03:42:56,426 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.30/linear_attn/out_proj/MatMul ...
2026-11-05 03:42:56,449 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.30/linear_attn/out_proj/MatMul with 4 bits ...
2026-11-05 03:42:56,449 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.30/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:56,449 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.30/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:56,602 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.30/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:56,602 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.30/mlp/gate_up_proj/Split ...
2026-11-05 03:42:56,602 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.30/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:56,602 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.30/mlp/act_fn/Mul ...
2026-11-05 03:42:56,602 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.30/mlp/Mul ...
2026-11-05 03:42:56,602 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.30/mlp/down_proj/MatMul ...
2026-11-05 03:42:56,654 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.30/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:56,654 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.31/input_layernorm/SkipLayerNorm ...
2026-11-05 03:42:56,654 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.31/attn/qkv_proj/MatMul ...
2026-11-05 03:42:56,717 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.31/attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:42:56,717 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.31/attn/qkv_proj/Split ...
2026-11-05 03:42:56,717 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.31/attn/q_gate/Reshape ...
2026-11-05 03:42:56,717 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.31/attn/q_gate/Split ...
2026-11-05 03:42:56,717 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.31/attn/q_proj/Reshape ...
2026-11-05 03:42:56,718 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.31/attn/gate/Reshape ...
2026-11-05 03:42:56,718 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.31/attn/q_norm/Reshape_1 ...
2026-11-05 03:42:56,718 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.31/attn/q_norm/SimplifiedLayerNormalization ...
2026-11-05 03:42:56,718 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.31/attn/q_norm/Reshape_2 ...
2026-11-05 03:42:56,718 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.31/attn/k_norm/Reshape_1 ...
2026-11-05 03:42:56,718 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.31/attn/k_norm/SimplifiedLayerNormalization ...
2026-11-05 03:42:56,718 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.31/attn/k_norm/Reshape_2 ...
2026-11-05 03:42:56,718 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.31/attn/q_rotary/MRotaryEmbedding ...
2026-11-05 03:42:56,718 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.31/attn/k_rotary/MRotaryEmbedding ...
2026-11-05 03:42:56,718 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.31/attn/GroupQueryAttention ...
2026-11-05 03:42:56,718 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.31/attn/gate/Sigmoid ...
2026-11-05 03:42:56,718 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.31/attn/gate/Mul ...
2026-11-05 03:42:56,718 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.31/attn/o_proj/MatMul ...
2026-11-05 03:42:56,731 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.31/attn/o_proj/MatMul with 4 bits ...
2026-11-05 03:42:56,731 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.31/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:42:56,731 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.31/mlp/gate_up_proj/MatMul ...
2026-11-05 03:42:56,856 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.31/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:42:56,856 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.31/mlp/gate_up_proj/Split ...
2026-11-05 03:42:56,856 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.31/mlp/act_fn/Sigmoid ...
2026-11-05 03:42:56,856 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.31/mlp/act_fn/Mul ...
2026-11-05 03:42:56,856 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.31/mlp/Mul ...
2026-11-05 03:42:56,856 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.31/mlp/down_proj/MatMul ...
2026-11-05 03:42:56,906 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.31/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:42:56,906 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.32/final_norm_layernorm/SkipLayerNorm ...
2026-11-05 03:42:56,906 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /lm_head/MatMul ...
2026-11-05 03:42:59,292 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /lm_head/MatMul with 4 bits ...
Reading embedding layer
Reading layer 0
Reading layer 1
Reading layer 2
Reading layer 3
Reading layer 4
Reading layer 5
Reading layer 6
Reading layer 7
Reading layer 8
Reading layer 9
Reading layer 10
Reading layer 11
Reading layer 12
Reading layer 13
Reading layer 14
Reading layer 15
Reading layer 16
Reading layer 17
Reading layer 18
Reading layer 19
Reading layer 20
Reading layer 21
Reading layer 22
Reading layer 23
Reading layer 24
Reading layer 25
Reading layer 26
Reading layer 27
Reading layer 28
Reading layer 29
Reading layer 30
Reading layer 31
Reading final norm
Reading LM head
Building MTP (multi-token prediction) head -> mtp.onnx
Saving ONNX model in /home/anon/knowline/onnx/model-cpu

0it [00:00, ?it/s]
Saving model.layers.0.input_layernorm.weight (f32, [2560]):   0%|          | 1/557 [00:00<00:04, 132.46it/s]
Saving model.layers.0.linear_attn.b_proj.MatMul.weight (f32, [2560,32]):   0%|          | 2/557 [00:00<00:02, 261.56it/s]
Saving model.layers.0.linear_attn.a_proj.MatMul.weight (f32, [2560,32]):   1%|          | 3/557 [00:00<00:01, 383.04it/s]
Saving model.layers.0.linear_attn.conv1d.weight (f32, [8192,1,4]):   1%|          | 4/557 [00:00<00:01, 504.65it/s]      
Saving model.layers.0.linear_attn.conv1d.bias (f32, [8192]):   1%|          | 5/557 [00:00<00:00, 625.77it/s]      
Saving model.layers.0.linear_attn.dt_bias (f32, [32]):   1%|          | 6/557 [00:00<00:00, 747.03it/s]      
Saving model.layers.0.linear_attn.neg_exp_A (f32, [32]):   1%|▏         | 7/557 [00:00<00:00, 869.00it/s]
Saving model.layers.0.linear_attn.norm.weight (f32, [128]):   1%|▏         | 8/557 [00:00<00:00, 989.69it/s]
Saving model.layers.0.post_attention_layernorm.weight (f32, [2560]):   2%|▏         | 9/557 [00:00<00:00, 1109.93it/s]
Saving model.layers.1.input_layernorm.weight (f32, [2560]):   2%|▏         | 10/557 [00:00<00:00, 1228.06it/s]        
Saving model.layers.1.linear_attn.b_proj.MatMul.weight (f32, [2560,32]):   2%|▏         | 11/557 [00:00<00:00, 1345.58it/s]
Saving model.layers.1.linear_attn.a_proj.MatMul.weight (f32, [2560,32]):   2%|▏         | 12/557 [00:00<00:00, 1453.37it/s]
Saving model.layers.1.linear_attn.conv1d.weight (f32, [8192,1,4]):   2%|▏         | 13/557 [00:00<00:00, 1559.04it/s]      
Saving model.layers.1.linear_attn.conv1d.bias (f32, [8192]):   3%|▎         | 14/557 [00:00<00:00, 1657.92it/s]      
Saving model.layers.1.linear_attn.dt_bias (f32, [32]):   3%|▎         | 15/557 [00:00<00:00, 1767.46it/s]      
Saving model.layers.1.linear_attn.neg_exp_A (f32, [32]):   3%|▎         | 16/557 [00:00<00:00, 1880.27it/s]
Saving model.layers.1.linear_attn.norm.weight (f32, [128]):   3%|▎         | 17/557 [00:00<00:00, 1991.93it/s]
Saving model.layers.1.post_attention_layernorm.weight (f32, [2560]):   3%|▎         | 18/557 [00:00<00:00, 2103.29it/s]
Saving model.layers.2.input_layernorm.weight (f32, [2560]):   3%|▎         | 19/557 [00:00<00:00, 2212.31it/s]         
Saving model.layers.2.linear_attn.b_proj.MatMul.weight (f32, [2560,32]):   4%|▎         | 20/557 [00:00<00:00, 2321.14it/s]
Saving model.layers.2.linear_attn.a_proj.MatMul.weight (f32, [2560,32]):   4%|▍         | 21/557 [00:00<00:00, 2415.48it/s]
Saving model.layers.2.linear_attn.conv1d.weight (f32, [8192,1,4]):   4%|▍         | 22/557 [00:00<00:00, 2505.56it/s]      
Saving model.layers.2.linear_attn.conv1d.bias (f32, [8192]):   4%|▍         | 23/557 [00:00<00:00, 2603.61it/s]      
Saving model.layers.2.linear_attn.dt_bias (f32, [32]):   4%|▍         | 24/557 [00:00<00:00, 2705.78it/s]      
Saving model.layers.2.linear_attn.neg_exp_A (f32, [32]):   4%|▍         | 25/557 [00:00<00:00, 2811.35it/s]
Saving model.layers.2.linear_attn.norm.weight (f32, [128]):   5%|▍         | 26/557 [00:00<00:00, 2915.83it/s]
Saving model.layers.2.post_attention_layernorm.weight (f32, [2560]):   5%|▍         | 27/557 [00:00<00:00, 3020.22it/s]
Saving model.layers.3.input_layernorm.weight (f32, [2560]):   5%|▌         | 28/557 [00:00<00:00, 3120.68it/s]         
Saving model.layers.3.attn.q_norm.layernorm.weight (f32, [256]):   5%|▌         | 29/557 [00:00<00:00, 3221.18it/s]
Saving model.layers.3.attn.k_norm.layernorm.weight (f32, [256]):   5%|▌         | 30/557 [00:00<00:00, 3323.80it/s]
Saving cos_cache (f32, [262144,32]):   6%|▌         | 31/557 [00:00<00:00, 3425.46it/s]                            
Saving sin_cache (f32, [262144,32]):   6%|▌         | 32/557 [00:00<00:00, 670.12it/s] 
Saving model.layers.3.post_attention_layernorm.weight (f32, [2560]):   6%|▌         | 33/557 [00:00<00:01, 475.07it/s]
Saving model.layers.4.input_layernorm.weight (f32, [2560]):   6%|▌         | 34/557 [00:00<00:01, 488.71it/s]         
Saving model.layers.4.linear_attn.b_proj.MatMul.weight (f32, [2560,32]):   6%|▋         | 35/557 [00:00<00:01, 502.78it/s]
Saving model.layers.4.linear_attn.a_proj.MatMul.weight (f32, [2560,32]):   6%|▋         | 36/557 [00:00<00:01, 516.44it/s]
Saving model.layers.4.linear_attn.conv1d.weight (f32, [8192,1,4]):   7%|▋         | 37/557 [00:00<00:00, 530.16it/s]      
Saving model.layers.4.linear_attn.conv1d.bias (f32, [8192]):   7%|▋         | 38/557 [00:00<00:00, 544.05it/s]      
Saving model.layers.4.linear_attn.dt_bias (f32, [32]):   7%|▋         | 39/557 [00:00<00:00, 558.07it/s]      
Saving model.layers.4.linear_attn.neg_exp_A (f32, [32]):   7%|▋         | 40/557 [00:00<00:00, 572.20it/s]
Saving model.layers.4.linear_attn.norm.weight (f32, [128]):   7%|▋         | 41/557 [00:00<00:00, 586.30it/s]
Saving model.layers.4.post_attention_layernorm.weight (f32, [2560]):   8%|▊         | 42/557 [00:00<00:00, 600.41it/s]
Saving model.layers.5.input_layernorm.weight (f32, [2560]):   8%|▊         | 43/557 [00:00<00:00, 614.43it/s]         
Saving model.layers.5.linear_attn.b_proj.MatMul.weight (f32, [2560,32]):   8%|▊         | 44/557 [00:00<00:00, 628.44it/s]
Saving model.layers.5.linear_attn.a_proj.MatMul.weight (f32, [2560,32]):   8%|▊         | 45/557 [00:00<00:00, 642.04it/s]
Saving model.layers.5.linear_attn.conv1d.weight (f32, [8192,1,4]):   8%|▊         | 46/557 [00:00<00:00, 655.52it/s]      
Saving model.layers.5.linear_attn.conv1d.bias (f32, [8192]):   8%|▊         | 47/557 [00:00<00:00, 669.16it/s]      
Saving model.layers.5.linear_attn.dt_bias (f32, [32]):   9%|▊         | 48/557 [00:00<00:00, 683.01it/s]      
Saving model.layers.5.linear_attn.neg_exp_A (f32, [32]):   9%|▉         | 49/557 [00:00<00:00, 697.02it/s]
Saving model.layers.5.linear_attn.norm.weight (f32, [128]):   9%|▉         | 50/557 [00:00<00:00, 711.01it/s]
Saving model.layers.5.post_attention_layernorm.weight (f32, [2560]):   9%|▉         | 51/557 [00:00<00:00, 725.01it/s]
Saving model.layers.6.input_layernorm.weight (f32, [2560]):   9%|▉         | 52/557 [00:00<00:00, 738.84it/s]         
Saving model.layers.6.linear_attn.b_proj.MatMul.weight (f32, [2560,32]):  10%|▉         | 53/557 [00:00<00:00, 752.74it/s]
Saving model.layers.6.linear_attn.a_proj.MatMul.weight (f32, [2560,32]):  10%|▉         | 54/557 [00:00<00:00, 766.19it/s]
Saving model.layers.6.linear_attn.conv1d.weight (f32, [8192,1,4]):  10%|▉         | 55/557 [00:00<00:00, 779.53it/s]      
Saving model.layers.6.linear_attn.conv1d.bias (f32, [8192]):  10%|█         | 56/557 [00:00<00:00, 793.07it/s]      
Saving model.layers.6.linear_attn.dt_bias (f32, [32]):  10%|█         | 57/557 [00:00<00:00, 806.80it/s]      
Saving model.layers.6.linear_attn.neg_exp_A (f32, [32]):  10%|█         | 58/557 [00:00<00:00, 820.70it/s]
Saving model.layers.6.linear_attn.norm.weight (f32, [128]):  11%|█         | 59/557 [00:00<00:00, 834.57it/s]
Saving model.layers.6.post_attention_layernorm.weight (f32, [2560]):  11%|█         | 60/557 [00:00<00:00, 848.45it/s]
Saving model.layers.7.input_layernorm.weight (f32, [2560]):  11%|█         | 61/557 [00:00<00:00, 862.23it/s]         
Saving model.layers.7.attn.q_norm.layernorm.weight (f32, [256]):  11%|█         | 62/557 [00:00<00:00, 876.00it/s]
Saving model.layers.7.attn.k_norm.layernorm.weight (f32, [256]):  11%|█▏        | 63/557 [00:00<00:00, 889.88it/s]
Saving model.layers.7.post_attention_layernorm.weight (f32, [2560]):  11%|█▏        | 64/557 [00:00<00:00, 903.68it/s]
Saving model.layers.8.input_layernorm.weight (f32, [2560]):  12%|█▏        | 65/557 [00:00<00:00, 917.41it/s]         
Saving model.layers.8.linear_attn.b_proj.MatMul.weight (f32, [2560,32]):  12%|█▏        | 66/557 [00:00<00:00, 931.16it/s]
Saving model.layers.8.linear_attn.a_proj.MatMul.weight (f32, [2560,32]):  12%|█▏        | 67/557 [00:00<00:00, 944.39it/s]
Saving model.layers.8.linear_attn.conv1d.weight (f32, [8192,1,4]):  12%|█▏        | 68/557 [00:00<00:00, 957.51it/s]      
Saving model.layers.8.linear_attn.conv1d.bias (f32, [8192]):  12%|█▏        | 69/557 [00:00<00:00, 970.94it/s]      
Saving model.layers.8.linear_attn.dt_bias (f32, [32]):  13%|█▎        | 70/557 [00:00<00:00, 984.49it/s]      
Saving model.layers.8.linear_attn.neg_exp_A (f32, [32]):  13%|█▎        | 71/557 [00:00<00:00, 998.27it/s]
Saving model.layers.8.linear_attn.norm.weight (f32, [128]):  13%|█▎        | 72/557 [00:00<00:00, 1012.02it/s]
Saving model.layers.8.post_attention_layernorm.weight (f32, [2560]):  13%|█▎        | 73/557 [00:00<00:00, 1025.70it/s]
Saving model.layers.9.input_layernorm.weight (f32, [2560]):  13%|█▎        | 74/557 [00:00<00:00, 1039.32it/s]         
Saving model.layers.9.linear_attn.b_proj.MatMul.weight (f32, [2560,32]):  13%|█▎        | 75/557 [00:00<00:00, 1052.97it/s]
Saving model.layers.9.linear_attn.a_proj.MatMul.weight (f32, [2560,32]):  14%|█▎        | 76/557 [00:00<00:00, 1065.73it/s]
Saving model.layers.9.linear_attn.conv1d.weight (f32, [8192,1,4]):  14%|█▍        | 77/557 [00:00<00:00, 1078.41it/s]      
Saving model.layers.9.linear_attn.conv1d.bias (f32, [8192]):  14%|█▍        | 78/557 [00:00<00:00, 1091.30it/s]      
Saving model.layers.9.linear_attn.dt_bias (f32, [32]):  14%|█▍        | 79/557 [00:00<00:00, 1104.52it/s]      
Saving model.layers.9.linear_attn.neg_exp_A (f32, [32]):  14%|█▍        | 80/557 [00:00<00:00, 1118.03it/s]
Saving model.layers.9.linear_attn.norm.weight (f32, [128]):  15%|█▍        | 81/557 [00:00<00:00, 1131.50it/s]
Saving model.layers.9.post_attention_layernorm.weight (f32, [2560]):  15%|█▍        | 82/557 [00:00<00:00, 1144.97it/s]
Saving model.layers.10.input_layernorm.weight (f32, [2560]):  15%|█▍        | 83/557 [00:00<00:00, 1158.29it/s]        
Saving model.layers.10.linear_attn.b_proj.MatMul.weight (f32, [2560,32]):  15%|█▌        | 84/557 [00:00<00:00, 1171.60it/s]
Saving model.layers.10.linear_attn.a_proj.MatMul.weight (f32, [2560,32]):  15%|█▌        | 85/557 [00:00<00:00, 1184.09it/s]
Saving model.layers.10.linear_attn.conv1d.weight (f32, [8192,1,4]):  15%|█▌        | 86/557 [00:00<00:00, 1196.34it/s]      
Saving model.layers.10.linear_attn.conv1d.bias (f32, [8192]):  16%|█▌        | 87/557 [00:00<00:00, 1209.03it/s]      
Saving model.layers.10.linear_attn.dt_bias (f32, [32]):  16%|█▌        | 88/557 [00:00<00:00, 1222.12it/s]      
Saving model.layers.10.linear_attn.neg_exp_A (f32, [32]):  16%|█▌        | 89/557 [00:00<00:00, 1235.49it/s]
Saving model.layers.10.linear_attn.norm.weight (f32, [128]):  16%|█▌        | 90/557 [00:00<00:00, 1248.81it/s]
Saving model.layers.10.post_attention_layernorm.weight (f32, [2560]):  16%|█▋        | 91/557 [00:00<00:00, 1262.06it/s]
Saving model.layers.11.input_layernorm.weight (f32, [2560]):  17%|█▋        | 92/557 [00:00<00:00, 1275.20it/s]         
Saving model.layers.11.attn.q_norm.layernorm.weight (f32, [256]):  17%|█▋        | 93/557 [00:00<00:00, 1288.27it/s]
Saving model.layers.11.attn.k_norm.layernorm.weight (f32, [256]):  17%|█▋        | 94/557 [00:00<00:00, 1301.56it/s]
Saving model.layers.11.post_attention_layernorm.weight (f32, [2560]):  17%|█▋        | 95/557 [00:00<00:00, 1314.81it/s]
Saving model.layers.12.input_layernorm.weight (f32, [2560]):  17%|█▋        | 96/557 [00:00<00:00, 1327.88it/s]         
Saving model.layers.12.linear_attn.b_proj.MatMul.weight (f32, [2560,32]):  17%|█▋        | 97/557 [00:00<00:00, 1340.93it/s]
Saving model.layers.12.linear_attn.a_proj.MatMul.weight (f32, [2560,32]):  18%|█▊        | 98/557 [00:00<00:00, 1352.34it/s]
Saving model.layers.12.linear_attn.conv1d.weight (f32, [8192,1,4]):  18%|█▊        | 99/557 [00:00<00:00, 1364.33it/s]      
Saving model.layers.12.linear_attn.conv1d.bias (f32, [8192]):  18%|█▊        | 100/557 [00:00<00:00, 1377.01it/s]     
Saving model.layers.12.linear_attn.dt_bias (f32, [32]):  18%|█▊        | 101/557 [00:00<00:00, 1390.05it/s]      
Saving model.layers.12.linear_attn.neg_exp_A (f32, [32]):  18%|█▊        | 102/557 [00:00<00:00, 1403.40it/s]
Saving model.layers.12.linear_attn.norm.weight (f32, [128]):  18%|█▊        | 103/557 [00:00<00:00, 1416.71it/s]
Saving model.layers.12.post_attention_layernorm.weight (f32, [2560]):  19%|█▊        | 104/557 [00:00<00:00, 1430.03it/s]
Saving model.layers.13.input_layernorm.weight (f32, [2560]):  19%|█▉        | 105/557 [00:00<00:00, 1443.19it/s]         
Saving model.layers.13.linear_attn.b_proj.MatMul.weight (f32, [2560,32]):  19%|█▉        | 106/557 [00:00<00:00, 1456.39it/s]
Saving model.layers.13.linear_attn.a_proj.MatMul.weight (f32, [2560,32]):  19%|█▉        | 107/557 [00:00<00:00, 1468.57it/s]
Saving model.layers.13.linear_attn.conv1d.weight (f32, [8192,1,4]):  19%|█▉        | 108/557 [00:00<00:00, 1480.73it/s]      
Saving model.layers.13.linear_attn.conv1d.bias (f32, [8192]):  20%|█▉        | 109/557 [00:00<00:00, 1493.21it/s]      
Saving model.layers.13.linear_attn.dt_bias (f32, [32]):  20%|█▉        | 110/557 [00:00<00:00, 1505.81it/s]      
Saving model.layers.13.linear_attn.neg_exp_A (f32, [32]):  20%|█▉        | 111/557 [00:00<00:00, 1518.83it/s]
Saving model.layers.13.linear_attn.norm.weight (f32, [128]):  20%|██        | 112/557 [00:00<00:00, 1531.73it/s]
Saving model.layers.13.post_attention_layernorm.weight (f32, [2560]):  20%|██        | 113/557 [00:00<00:00, 1544.59it/s]
Saving model.layers.14.input_layernorm.weight (f32, [2560]):  20%|██        | 114/557 [00:00<00:00, 1557.19it/s]         
Saving model.layers.14.linear_attn.b_proj.MatMul.weight (f32, [2560,32]):  21%|██        | 115/557 [00:00<00:00, 1569.90it/s]
Saving model.layers.14.linear_attn.a_proj.MatMul.weight (f32, [2560,32]):  21%|██        | 116/557 [00:00<00:00, 1581.42it/s]
Saving model.layers.14.linear_attn.conv1d.weight (f32, [8192,1,4]):  21%|██        | 117/557 [00:00<00:00, 1592.90it/s]      
Saving model.layers.14.linear_attn.conv1d.bias (f32, [8192]):  21%|██        | 118/557 [00:00<00:00, 1604.94it/s]      
Saving model.layers.14.linear_attn.dt_bias (f32, [32]):  21%|██▏       | 119/557 [00:00<00:00, 1617.37it/s]      
Saving model.layers.14.linear_attn.neg_exp_A (f32, [32]):  22%|██▏       | 120/557 [00:00<00:00, 1630.37it/s]
Saving model.layers.14.linear_attn.norm.weight (f32, [128]):  22%|██▏       | 121/557 [00:00<00:00, 1643.34it/s]
Saving model.layers.14.post_attention_layernorm.weight (f32, [2560]):  22%|██▏       | 122/557 [00:00<00:00, 1656.37it/s]
Saving model.layers.15.input_layernorm.weight (f32, [2560]):  22%|██▏       | 123/557 [00:00<00:00, 1669.25it/s]         
Saving model.layers.15.attn.q_norm.layernorm.weight (f32, [256]):  22%|██▏       | 124/557 [00:00<00:00, 1682.13it/s]
Saving model.layers.15.attn.k_norm.layernorm.weight (f32, [256]):  22%|██▏       | 125/557 [00:00<00:00, 1695.19it/s]
Saving model.layers.15.post_attention_layernorm.weight (f32, [2560]):  23%|██▎       | 126/557 [00:00<00:00, 1708.17it/s]
Saving model.layers.16.input_layernorm.weight (f32, [2560]):  23%|██▎       | 127/557 [00:00<00:00, 1720.97it/s]         
Saving model.layers.16.linear_attn.b_proj.MatMul.weight (f32, [2560,32]):  23%|██▎       | 128/557 [00:00<00:00, 1733.82it/s]
Saving model.layers.16.linear_attn.a_proj.MatMul.weight (f32, [2560,32]):  23%|██▎       | 129/557 [00:00<00:00, 1745.69it/s]
Saving model.layers.16.linear_attn.conv1d.weight (f32, [8192,1,4]):  23%|██▎       | 130/557 [00:00<00:00, 1757.21it/s]      
Saving model.layers.16.linear_attn.conv1d.bias (f32, [8192]):  24%|██▎       | 131/557 [00:00<00:00, 1769.17it/s]      
Saving model.layers.16.linear_attn.dt_bias (f32, [32]):  24%|██▎       | 132/557 [00:00<00:00, 1781.70it/s]      
Saving model.layers.16.linear_attn.neg_exp_A (f32, [32]):  24%|██▍       | 133/557 [00:00<00:00, 1794.68it/s]
Saving model.layers.16.linear_attn.norm.weight (f32, [128]):  24%|██▍       | 134/557 [00:00<00:00, 1807.56it/s]
Saving model.layers.16.post_attention_layernorm.weight (f32, [2560]):  24%|██▍       | 135/557 [00:00<00:00, 1820.40it/s]
Saving model.layers.17.input_layernorm.weight (f32, [2560]):  24%|██▍       | 136/557 [00:00<00:00, 1833.04it/s]         
Saving model.layers.17.linear_attn.b_proj.MatMul.weight (f32, [2560,32]):  25%|██▍       | 137/557 [00:00<00:00, 1845.68it/s]
Saving model.layers.17.linear_attn.a_proj.MatMul.weight (f32, [2560,32]):  25%|██▍       | 138/557 [00:00<00:00, 1857.04it/s]
Saving model.layers.17.linear_attn.conv1d.weight (f32, [8192,1,4]):  25%|██▍       | 139/557 [00:00<00:00, 1868.13it/s]      
Saving model.layers.17.linear_attn.conv1d.bias (f32, [8192]):  25%|██▌       | 140/557 [00:00<00:00, 1879.82it/s]      
Saving model.layers.17.linear_attn.dt_bias (f32, [32]):  25%|██▌       | 141/557 [00:00<00:00, 1892.03it/s]      
Saving model.layers.17.linear_attn.neg_exp_A (f32, [32]):  25%|██▌       | 142/557 [00:00<00:00, 1904.89it/s]
Saving model.layers.17.linear_attn.norm.weight (f32, [128]):  26%|██▌       | 143/557 [00:00<00:00, 1917.63it/s]
Saving model.layers.17.post_attention_layernorm.weight (f32, [2560]):  26%|██▌       | 144/557 [00:00<00:00, 1930.43it/s]
Saving model.layers.18.input_layernorm.weight (f32, [2560]):  26%|██▌       | 145/557 [00:00<00:00, 1942.88it/s]         
Saving model.layers.18.linear_attn.b_proj.MatMul.weight (f32, [2560,32]):  26%|██▌       | 146/557 [00:00<00:00, 1955.35it/s]
Saving model.layers.18.linear_attn.a_proj.MatMul.weight (f32, [2560,32]):  26%|██▋       | 147/557 [00:00<00:00, 1966.49it/s]
Saving model.layers.18.linear_attn.conv1d.weight (f32, [8192,1,4]):  27%|██▋       | 148/557 [00:00<00:00, 1977.82it/s]      
Saving model.layers.18.linear_attn.conv1d.bias (f32, [8192]):  27%|██▋       | 149/557 [00:00<00:00, 1989.79it/s]      
Saving model.layers.18.linear_attn.dt_bias (f32, [32]):  27%|██▋       | 150/557 [00:00<00:00, 2002.11it/s]      
Saving model.layers.18.linear_attn.neg_exp_A (f32, [32]):  27%|██▋       | 151/557 [00:00<00:00, 2014.86it/s]
Saving model.layers.18.linear_attn.norm.weight (f32, [128]):  27%|██▋       | 152/557 [00:00<00:00, 2027.51it/s]
Saving model.layers.18.post_attention_layernorm.weight (f32, [2560]):  27%|██▋       | 153/557 [00:00<00:00, 2040.21it/s]
Saving model.layers.19.input_layernorm.weight (f32, [2560]):  28%|██▊       | 154/557 [00:00<00:00, 2052.67it/s]         
Saving model.layers.19.attn.q_norm.layernorm.weight (f32, [256]):  28%|██▊       | 155/557 [00:00<00:00, 2065.16it/s]
Saving model.layers.19.attn.k_norm.layernorm.weight (f32, [256]):  28%|██▊       | 156/557 [00:00<00:00, 2077.88it/s]
Saving model.layers.19.post_attention_layernorm.weight (f32, [2560]):  28%|██▊       | 157/557 [00:00<00:00, 2090.51it/s]
Saving model.layers.20.input_layernorm.weight (f32, [2560]):  28%|██▊       | 158/557 [00:00<00:00, 2102.93it/s]         
Saving model.layers.20.linear_attn.b_proj.MatMul.weight (f32, [2560,32]):  29%|██▊       | 159/557 [00:00<00:00, 2115.26it/s]
Saving model.layers.20.linear_attn.a_proj.MatMul.weight (f32, [2560,32]):  29%|██▊       | 160/557 [00:00<00:00, 2126.32it/s]
Saving model.layers.20.linear_attn.conv1d.weight (f32, [8192,1,4]):  29%|██▉       | 161/557 [00:00<00:00, 2137.38it/s]      
Saving model.layers.20.linear_attn.conv1d.bias (f32, [8192]):  29%|██▉       | 162/557 [00:00<00:00, 2148.63it/s]      
Saving model.layers.20.linear_attn.dt_bias (f32, [32]):  29%|██▉       | 163/557 [00:00<00:00, 2160.67it/s]      
Saving model.layers.20.linear_attn.neg_exp_A (f32, [32]):  29%|██▉       | 164/557 [00:00<00:00, 2173.23it/s]
Saving model.layers.20.linear_attn.norm.weight (f32, [128]):  30%|██▉       | 165/557 [00:00<00:00, 2185.76it/s]
Saving model.layers.20.post_attention_layernorm.weight (f32, [2560]):  30%|██▉       | 166/557 [00:00<00:00, 2198.29it/s]
Saving model.layers.21.input_layernorm.weight (f32, [2560]):  30%|██▉       | 167/557 [00:00<00:00, 2210.53it/s]         
Saving model.layers.21.linear_attn.b_proj.MatMul.weight (f32, [2560,32]):  30%|███       | 168/557 [00:00<00:00, 2222.87it/s]
Saving model.layers.21.linear_attn.a_proj.MatMul.weight (f32, [2560,32]):  30%|███       | 169/557 [00:00<00:00, 2233.83it/s]
Saving model.layers.21.linear_attn.conv1d.weight (f32, [8192,1,4]):  31%|███       | 170/557 [00:00<00:00, 2244.45it/s]      
Saving model.layers.21.linear_attn.conv1d.bias (f32, [8192]):  31%|███       | 171/557 [00:00<00:00, 2256.04it/s]      
Saving model.layers.21.linear_attn.dt_bias (f32, [32]):  31%|███       | 172/557 [00:00<00:00, 2268.09it/s]      
Saving model.layers.21.linear_attn.neg_exp_A (f32, [32]):  31%|███       | 173/557 [00:00<00:00, 2280.62it/s]
Saving model.layers.21.linear_attn.norm.weight (f32, [128]):  31%|███       | 174/557 [00:00<00:00, 2293.05it/s]
Saving model.layers.21.post_attention_layernorm.weight (f32, [2560]):  31%|███▏      | 175/557 [00:00<00:00, 2301.72it/s]
Saving model.layers.22.input_layernorm.weight (f32, [2560]):  32%|███▏      | 176/557 [00:00<00:00, 2313.40it/s]         
Saving model.layers.22.linear_attn.b_proj.MatMul.weight (f32, [2560,32]):  32%|███▏      | 177/557 [00:00<00:00, 2325.49it/s]
Saving model.layers.22.linear_attn.a_proj.MatMul.weight (f32, [2560,32]):  32%|███▏      | 178/557 [00:00<00:00, 2335.88it/s]
Saving model.layers.22.linear_attn.conv1d.weight (f32, [8192,1,4]):  32%|███▏      | 179/557 [00:00<00:00, 2346.29it/s]      
Saving model.layers.22.linear_attn.conv1d.bias (f32, [8192]):  32%|███▏      | 180/557 [00:00<00:00, 2357.51it/s]      
Saving model.layers.22.linear_attn.dt_bias (f32, [32]):  32%|███▏      | 181/557 [00:00<00:00, 2369.26it/s]      
Saving model.layers.22.linear_attn.neg_exp_A (f32, [32]):  33%|███▎      | 182/557 [00:00<00:00, 2381.65it/s]
Saving model.layers.22.linear_attn.norm.weight (f32, [128]):  33%|███▎      | 183/557 [00:00<00:00, 2393.97it/s]
Saving model.layers.22.post_attention_layernorm.weight (f32, [2560]):  33%|███▎      | 184/557 [00:00<00:00, 2406.35it/s]
Saving model.layers.23.input_layernorm.weight (f32, [2560]):  33%|███▎      | 185/557 [00:00<00:00, 2418.38it/s]         
Saving model.layers.23.attn.q_norm.layernorm.weight (f32, [256]):  33%|███▎      | 186/557 [00:00<00:00, 2430.47it/s]
Saving model.layers.23.attn.k_norm.layernorm.weight (f32, [256]):  34%|███▎      | 187/557 [00:00<00:00, 2442.86it/s]
Saving model.layers.23.post_attention_layernorm.weight (f32, [2560]):  34%|███▍      | 188/557 [00:00<00:00, 2455.15it/s]
Saving model.layers.24.input_layernorm.weight (f32, [2560]):  34%|███▍      | 189/557 [00:00<00:00, 2467.12it/s]         
Saving model.layers.24.linear_attn.b_proj.MatMul.weight (f32, [2560,32]):  34%|███▍      | 190/557 [00:00<00:00, 2479.12it/s]
Saving model.layers.24.linear_attn.a_proj.MatMul.weight (f32, [2560,32]):  34%|███▍      | 191/557 [00:00<00:00, 2489.53it/s]
Saving model.layers.24.linear_attn.conv1d.weight (f32, [8192,1,4]):  34%|███▍      | 192/557 [00:00<00:00, 2500.07it/s]      
Saving model.layers.24.linear_attn.conv1d.bias (f32, [8192]):  35%|███▍      | 193/557 [00:00<00:00, 2511.22it/s]      
Saving model.layers.24.linear_attn.dt_bias (f32, [32]):  35%|███▍      | 194/557 [00:00<00:00, 2522.98it/s]      
Saving model.layers.24.linear_attn.neg_exp_A (f32, [32]):  35%|███▌      | 195/557 [00:00<00:00, 2535.23it/s]
Saving model.layers.24.linear_attn.norm.weight (f32, [128]):  35%|███▌      | 196/557 [00:00<00:00, 2547.38it/s]
Saving model.layers.24.post_attention_layernorm.weight (f32, [2560]):  35%|███▌      | 197/557 [00:00<00:00, 2559.63it/s]
Saving model.layers.25.input_layernorm.weight (f32, [2560]):  36%|███▌      | 198/557 [00:00<00:00, 2571.47it/s]         
Saving model.layers.25.linear_attn.b_proj.MatMul.weight (f32, [2560,32]):  36%|███▌      | 199/557 [00:00<00:00, 2583.46it/s]
Saving model.layers.25.linear_attn.a_proj.MatMul.weight (f32, [2560,32]):  36%|███▌      | 200/557 [00:00<00:00, 2593.50it/s]
Saving model.layers.25.linear_attn.conv1d.weight (f32, [8192,1,4]):  36%|███▌      | 201/557 [00:00<00:00, 2603.60it/s]      
Saving model.layers.25.linear_attn.conv1d.bias (f32, [8192]):  36%|███▋      | 202/557 [00:00<00:00, 2614.68it/s]      
Saving model.layers.25.linear_attn.dt_bias (f32, [32]):  36%|███▋      | 203/557 [00:00<00:00, 2626.40it/s]      
Saving model.layers.25.linear_attn.neg_exp_A (f32, [32]):  37%|███▋      | 204/557 [00:00<00:00, 2638.63it/s]
Saving model.layers.25.linear_attn.norm.weight (f32, [128]):  37%|███▋      | 205/557 [00:00<00:00, 2650.77it/s]
Saving model.layers.25.post_attention_layernorm.weight (f32, [2560]):  37%|███▋      | 206/557 [00:00<00:00, 2662.87it/s]
Saving model.layers.26.input_layernorm.weight (f32, [2560]):  37%|███▋      | 207/557 [00:00<00:00, 2674.42it/s]         
Saving model.layers.26.linear_attn.b_proj.MatMul.weight (f32, [2560,32]):  37%|███▋      | 208/557 [00:00<00:00, 2686.23it/s]
Saving model.layers.26.linear_attn.a_proj.MatMul.weight (f32, [2560,32]):  38%|███▊      | 209/557 [00:00<00:00, 2696.66it/s]
Saving model.layers.26.linear_attn.conv1d.weight (f32, [8192,1,4]):  38%|███▊      | 210/557 [00:00<00:00, 2707.02it/s]      
Saving model.layers.26.linear_attn.conv1d.bias (f32, [8192]):  38%|███▊      | 211/557 [00:00<00:00, 2718.25it/s]      
Saving model.layers.26.linear_attn.dt_bias (f32, [32]):  38%|███▊      | 212/557 [00:00<00:00, 2729.90it/s]      
Saving model.layers.26.linear_attn.neg_exp_A (f32, [32]):  38%|███▊      | 213/557 [00:00<00:00, 2742.07it/s]
Saving model.layers.26.linear_attn.norm.weight (f32, [128]):  38%|███▊      | 214/557 [00:00<00:00, 2754.09it/s]
Saving model.layers.26.post_attention_layernorm.weight (f32, [2560]):  39%|███▊      | 215/557 [00:00<00:00, 2766.17it/s]
Saving model.layers.27.input_layernorm.weight (f32, [2560]):  39%|███▉      | 216/557 [00:00<00:00, 2778.00it/s]         
Saving model.layers.27.attn.q_norm.layernorm.weight (f32, [256]):  39%|███▉      | 217/557 [00:00<00:00, 2789.83it/s]
Saving model.layers.27.attn.k_norm.layernorm.weight (f32, [256]):  39%|███▉      | 218/557 [00:00<00:00, 2801.96it/s]
Saving model.layers.27.post_attention_layernorm.weight (f32, [2560]):  39%|███▉      | 219/557 [00:00<00:00, 2813.96it/s]
Saving model.layers.28.input_layernorm.weight (f32, [2560]):  39%|███▉      | 220/557 [00:00<00:00, 2825.72it/s]         
Saving model.layers.28.linear_attn.b_proj.MatMul.weight (f32, [2560,32]):  40%|███▉      | 221/557 [00:00<00:00, 2837.40it/s]
Saving model.layers.28.linear_attn.a_proj.MatMul.weight (f32, [2560,32]):  40%|███▉      | 222/557 [00:00<00:00, 2847.75it/s]
Saving model.layers.28.linear_attn.conv1d.weight (f32, [8192,1,4]):  40%|████      | 223/557 [00:00<00:00, 2857.76it/s]      
Saving model.layers.28.linear_attn.conv1d.bias (f32, [8192]):  40%|████      | 224/557 [00:00<00:00, 2868.74it/s]      
Saving model.layers.28.linear_attn.dt_bias (f32, [32]):  40%|████      | 225/557 [00:00<00:00, 2880.25it/s]      
Saving model.layers.28.linear_attn.neg_exp_A (f32, [32]):  41%|████      | 226/557 [00:00<00:00, 2892.27it/s]
Saving model.layers.28.linear_attn.norm.weight (f32, [128]):  41%|████      | 227/557 [00:00<00:00, 2904.14it/s]
Saving model.layers.28.post_attention_layernorm.weight (f32, [2560]):  41%|████      | 228/557 [00:00<00:00, 2915.92it/s]
Saving model.layers.29.input_layernorm.weight (f32, [2560]):  41%|████      | 229/557 [00:00<00:00, 2927.52it/s]         
Saving model.layers.29.linear_attn.b_proj.MatMul.weight (f32, [2560,32]):  41%|████▏     | 230/557 [00:00<00:00, 2939.25it/s]
Saving model.layers.29.linear_attn.a_proj.MatMul.weight (f32, [2560,32]):  41%|████▏     | 231/557 [00:00<00:00, 2949.31it/s]
Saving model.layers.29.linear_attn.conv1d.weight (f32, [8192,1,4]):  42%|████▏     | 232/557 [00:00<00:00, 2958.24it/s]      
Saving model.layers.29.linear_attn.conv1d.bias (f32, [8192]):  42%|████▏     | 233/557 [00:00<00:00, 2968.86it/s]      
Saving model.layers.29.linear_attn.dt_bias (f32, [32]):  42%|████▏     | 234/557 [00:00<00:00, 2980.25it/s]      
Saving model.layers.29.linear_attn.neg_exp_A (f32, [32]):  42%|████▏     | 235/557 [00:00<00:00, 2992.18it/s]
Saving model.layers.29.linear_attn.norm.weight (f32, [128]):  42%|████▏     | 236/557 [00:00<00:00, 3004.03it/s]
Saving model.layers.29.post_attention_layernorm.weight (f32, [2560]):  43%|████▎     | 237/557 [00:00<00:00, 3015.93it/s]
Saving model.layers.30.input_layernorm.weight (f32, [2560]):  43%|████▎     | 238/557 [00:00<00:00, 3027.53it/s]         
Saving model.layers.30.linear_attn.b_proj.MatMul.weight (f32, [2560,32]):  43%|████▎     | 239/557 [00:00<00:00, 3039.17it/s]
Saving model.layers.30.linear_attn.a_proj.MatMul.weight (f32, [2560,32]):  43%|████▎     | 240/557 [00:00<00:00, 3048.94it/s]
Saving model.layers.30.linear_attn.conv1d.weight (f32, [8192,1,4]):  43%|████▎     | 241/557 [00:00<00:00, 3058.55it/s]      
Saving model.layers.30.linear_attn.conv1d.bias (f32, [8192]):  43%|████▎     | 242/557 [00:00<00:00, 3069.38it/s]      
Saving model.layers.30.linear_attn.dt_bias (f32, [32]):  44%|████▎     | 243/557 [00:00<00:00, 3080.65it/s]      
Saving model.layers.30.linear_attn.neg_exp_A (f32, [32]):  44%|████▍     | 244/557 [00:00<00:00, 3092.54it/s]
Saving model.layers.30.linear_attn.norm.weight (f32, [128]):  44%|████▍     | 245/557 [00:00<00:00, 3104.31it/s]
Saving model.layers.30.post_attention_layernorm.weight (f32, [2560]):  44%|████▍     | 246/557 [00:00<00:00, 3116.09it/s]
Saving model.layers.31.input_layernorm.weight (f32, [2560]):  44%|████▍     | 247/557 [00:00<00:00, 3127.58it/s]         
Saving model.layers.31.attn.q_norm.layernorm.weight (f32, [256]):  45%|████▍     | 248/557 [00:00<00:00, 3139.13it/s]
Saving model.layers.31.attn.k_norm.layernorm.weight (f32, [256]):  45%|████▍     | 249/557 [00:00<00:00, 3150.95it/s]
Saving model.layers.31.post_attention_layernorm.weight (f32, [2560]):  45%|████▍     | 250/557 [00:00<00:00, 3162.60it/s]
Saving model.layers.32.final_norm_layernorm.weight (f32, [2560]):  45%|████▌     | 251/557 [00:00<00:00, 3174.11it/s]    
Saving model.layers.0.linear_attn.qkv_proj.MatMul.weight_Q4 (u8, [8192,80,16]):  45%|████▌     | 252/557 [00:00<00:00, 3185.61it/s]
Saving model.layers.0.linear_attn.qkv_proj.MatMul.weight_scales (f32, [8192,80]):  45%|████▌     | 253/557 [00:00<00:00, 3142.49it/s]
Saving model.layers.0.linear_attn.z_proj.MatMul.weight_Q4 (u8, [4096,80,16]):  46%|████▌     | 254/557 [00:00<00:00, 3141.36it/s]    
Saving model.layers.0.linear_attn.z_proj.MatMul.weight_scales (f32, [4096,80]):  46%|████▌     | 255/557 [00:00<00:00, 3118.58it/s]
Saving model.layers.0.linear_attn.out_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  46%|████▌     | 256/557 [00:00<00:00, 3110.02it/s]
Saving model.layers.0.linear_attn.out_proj.MatMul.weight_scales (f32, [2560,128]):  46%|████▌     | 257/557 [00:00<00:00, 3097.67it/s]
Saving model.layers.0.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  46%|████▋     | 258/557 [00:00<00:00, 3102.85it/s]     
Saving model.layers.0.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  46%|████▋     | 259/557 [00:00<00:00, 2989.82it/s]
Saving model.layers.0.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  47%|████▋     | 260/557 [00:00<00:00, 2964.63it/s]      
Saving model.layers.0.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  47%|████▋     | 261/557 [00:00<00:00, 2918.34it/s]
Saving model.layers.0.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  47%|████▋     | 262/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.1.linear_attn.qkv_proj.MatMul.weight_Q4 (u8, [8192,80,16]):  47%|████▋     | 262/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.1.linear_attn.qkv_proj.MatMul.weight_scales (f32, [8192,80]):  47%|████▋     | 263/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.1.linear_attn.z_proj.MatMul.weight_Q4 (u8, [4096,80,16]):  47%|████▋     | 264/557 [00:00<00:00, 2292.53it/s]    
Saving model.layers.1.linear_attn.z_proj.MatMul.weight_scales (f32, [4096,80]):  48%|████▊     | 265/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.1.linear_attn.out_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  48%|████▊     | 266/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.1.linear_attn.out_proj.MatMul.weight_scales (f32, [2560,128]):  48%|████▊     | 267/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.1.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  48%|████▊     | 268/557 [00:00<00:00, 2292.53it/s]     
Saving model.layers.1.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  48%|████▊     | 269/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.1.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  48%|████▊     | 270/557 [00:00<00:00, 2292.53it/s]      
Saving model.layers.1.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  49%|████▊     | 271/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.2.linear_attn.qkv_proj.MatMul.weight_Q4 (u8, [8192,80,16]):  49%|████▉     | 272/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.2.linear_attn.qkv_proj.MatMul.weight_scales (f32, [8192,80]):  49%|████▉     | 273/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.2.linear_attn.z_proj.MatMul.weight_Q4 (u8, [4096,80,16]):  49%|████▉     | 274/557 [00:00<00:00, 2292.53it/s]    
Saving model.layers.2.linear_attn.z_proj.MatMul.weight_scales (f32, [4096,80]):  49%|████▉     | 275/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.2.linear_attn.out_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  50%|████▉     | 276/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.2.linear_attn.out_proj.MatMul.weight_scales (f32, [2560,128]):  50%|████▉     | 277/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.2.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  50%|████▉     | 278/557 [00:00<00:00, 2292.53it/s]     
Saving model.layers.2.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  50%|█████     | 279/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.2.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  50%|█████     | 280/557 [00:00<00:00, 2292.53it/s]      
Saving model.layers.2.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  50%|█████     | 281/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.3.attn.qkv_proj.MatMul.weight_Q4 (u8, [10240,80,16]):  51%|█████     | 282/557 [00:00<00:00, 2292.53it/s]  
Saving model.layers.3.attn.qkv_proj.MatMul.weight_scales (f32, [10240,80]):  51%|█████     | 283/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.3.attn.o_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  51%|█████     | 284/557 [00:00<00:00, 2292.53it/s]    
Saving model.layers.3.attn.o_proj.MatMul.weight_scales (f32, [2560,128]):  51%|█████     | 285/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.3.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  51%|█████▏    | 286/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.3.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  52%|█████▏    | 287/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.3.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  52%|█████▏    | 288/557 [00:00<00:00, 2292.53it/s]      
Saving model.layers.3.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  52%|█████▏    | 289/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.4.linear_attn.qkv_proj.MatMul.weight_Q4 (u8, [8192,80,16]):  52%|█████▏    | 290/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.4.linear_attn.qkv_proj.MatMul.weight_scales (f32, [8192,80]):  52%|█████▏    | 291/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.4.linear_attn.z_proj.MatMul.weight_Q4 (u8, [4096,80,16]):  52%|█████▏    | 292/557 [00:00<00:00, 2292.53it/s]    
Saving model.layers.4.linear_attn.z_proj.MatMul.weight_scales (f32, [4096,80]):  53%|█████▎    | 293/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.4.linear_attn.out_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  53%|█████▎    | 294/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.4.linear_attn.out_proj.MatMul.weight_scales (f32, [2560,128]):  53%|█████▎    | 295/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.4.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  53%|█████▎    | 296/557 [00:00<00:00, 2292.53it/s]     
Saving model.layers.4.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  53%|█████▎    | 297/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.4.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  54%|█████▎    | 298/557 [00:00<00:00, 2292.53it/s]      
Saving model.layers.4.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  54%|█████▎    | 299/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.5.linear_attn.qkv_proj.MatMul.weight_Q4 (u8, [8192,80,16]):  54%|█████▍    | 300/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.5.linear_attn.qkv_proj.MatMul.weight_scales (f32, [8192,80]):  54%|█████▍    | 301/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.5.linear_attn.z_proj.MatMul.weight_Q4 (u8, [4096,80,16]):  54%|█████▍    | 302/557 [00:00<00:00, 2292.53it/s]    
Saving model.layers.5.linear_attn.z_proj.MatMul.weight_scales (f32, [4096,80]):  54%|█████▍    | 303/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.5.linear_attn.out_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  55%|█████▍    | 304/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.5.linear_attn.out_proj.MatMul.weight_scales (f32, [2560,128]):  55%|█████▍    | 305/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.5.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  55%|█████▍    | 306/557 [00:00<00:00, 2292.53it/s]     
Saving model.layers.5.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  55%|█████▌    | 307/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.5.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  55%|█████▌    | 308/557 [00:00<00:00, 2292.53it/s]      
Saving model.layers.5.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  55%|█████▌    | 309/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.6.linear_attn.qkv_proj.MatMul.weight_Q4 (u8, [8192,80,16]):  56%|█████▌    | 310/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.6.linear_attn.qkv_proj.MatMul.weight_scales (f32, [8192,80]):  56%|█████▌    | 311/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.6.linear_attn.z_proj.MatMul.weight_Q4 (u8, [4096,80,16]):  56%|█████▌    | 312/557 [00:00<00:00, 2292.53it/s]    
Saving model.layers.6.linear_attn.z_proj.MatMul.weight_scales (f32, [4096,80]):  56%|█████▌    | 313/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.6.linear_attn.out_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  56%|█████▋    | 314/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.6.linear_attn.out_proj.MatMul.weight_scales (f32, [2560,128]):  57%|█████▋    | 315/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.6.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  57%|█████▋    | 316/557 [00:00<00:00, 2292.53it/s]     
Saving model.layers.6.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  57%|█████▋    | 317/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.6.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  57%|█████▋    | 318/557 [00:00<00:00, 2292.53it/s]      
Saving model.layers.6.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  57%|█████▋    | 319/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.7.attn.qkv_proj.MatMul.weight_Q4 (u8, [10240,80,16]):  57%|█████▋    | 320/557 [00:00<00:00, 2292.53it/s]  
Saving model.layers.7.attn.qkv_proj.MatMul.weight_scales (f32, [10240,80]):  58%|█████▊    | 321/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.7.attn.o_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  58%|█████▊    | 322/557 [00:00<00:00, 2292.53it/s]    
Saving model.layers.7.attn.o_proj.MatMul.weight_scales (f32, [2560,128]):  58%|█████▊    | 323/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.7.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  58%|█████▊    | 324/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.7.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  58%|█████▊    | 325/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.7.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  59%|█████▊    | 326/557 [00:00<00:00, 2292.53it/s]      
Saving model.layers.7.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  59%|█████▊    | 327/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.8.linear_attn.qkv_proj.MatMul.weight_Q4 (u8, [8192,80,16]):  59%|█████▉    | 328/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.8.linear_attn.qkv_proj.MatMul.weight_scales (f32, [8192,80]):  59%|█████▉    | 329/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.8.linear_attn.z_proj.MatMul.weight_Q4 (u8, [4096,80,16]):  59%|█████▉    | 330/557 [00:00<00:00, 2292.53it/s]    
Saving model.layers.8.linear_attn.z_proj.MatMul.weight_scales (f32, [4096,80]):  59%|█████▉    | 331/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.8.linear_attn.out_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  60%|█████▉    | 332/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.8.linear_attn.out_proj.MatMul.weight_scales (f32, [2560,128]):  60%|█████▉    | 333/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.8.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  60%|█████▉    | 334/557 [00:00<00:00, 2292.53it/s]     
Saving model.layers.8.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  60%|██████    | 335/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.8.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  60%|██████    | 336/557 [00:00<00:00, 2292.53it/s]      
Saving model.layers.8.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  61%|██████    | 337/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.9.linear_attn.qkv_proj.MatMul.weight_Q4 (u8, [8192,80,16]):  61%|██████    | 338/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.9.linear_attn.qkv_proj.MatMul.weight_scales (f32, [8192,80]):  61%|██████    | 339/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.9.linear_attn.z_proj.MatMul.weight_Q4 (u8, [4096,80,16]):  61%|██████    | 340/557 [00:00<00:00, 2292.53it/s]    
Saving model.layers.9.linear_attn.z_proj.MatMul.weight_scales (f32, [4096,80]):  61%|██████    | 341/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.9.linear_attn.out_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  61%|██████▏   | 342/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.9.linear_attn.out_proj.MatMul.weight_scales (f32, [2560,128]):  62%|██████▏   | 343/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.9.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  62%|██████▏   | 344/557 [00:00<00:00, 2292.53it/s]     
Saving model.layers.9.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  62%|██████▏   | 345/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.9.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  62%|██████▏   | 346/557 [00:00<00:00, 2292.53it/s]      
Saving model.layers.9.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  62%|██████▏   | 347/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.10.linear_attn.qkv_proj.MatMul.weight_Q4 (u8, [8192,80,16]):  62%|██████▏   | 348/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.10.linear_attn.qkv_proj.MatMul.weight_scales (f32, [8192,80]):  63%|██████▎   | 349/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.10.linear_attn.z_proj.MatMul.weight_Q4 (u8, [4096,80,16]):  63%|██████▎   | 350/557 [00:00<00:00, 2292.53it/s]    
Saving model.layers.10.linear_attn.z_proj.MatMul.weight_scales (f32, [4096,80]):  63%|██████▎   | 351/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.10.linear_attn.out_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  63%|██████▎   | 352/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.10.linear_attn.out_proj.MatMul.weight_scales (f32, [2560,128]):  63%|██████▎   | 353/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.10.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  64%|██████▎   | 354/557 [00:00<00:00, 2292.53it/s]     
Saving model.layers.10.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  64%|██████▎   | 355/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.10.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  64%|██████▍   | 356/557 [00:00<00:00, 2292.53it/s]      
Saving model.layers.10.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  64%|██████▍   | 357/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.11.attn.qkv_proj.MatMul.weight_Q4 (u8, [10240,80,16]):  64%|██████▍   | 358/557 [00:00<00:00, 2292.53it/s]  
Saving model.layers.11.attn.qkv_proj.MatMul.weight_scales (f32, [10240,80]):  64%|██████▍   | 359/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.11.attn.o_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  65%|██████▍   | 360/557 [00:00<00:00, 2292.53it/s]    
Saving model.layers.11.attn.o_proj.MatMul.weight_scales (f32, [2560,128]):  65%|██████▍   | 361/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.11.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  65%|██████▍   | 362/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.11.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  65%|██████▌   | 363/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.11.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  65%|██████▌   | 364/557 [00:00<00:00, 2292.53it/s]      
Saving model.layers.11.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  66%|██████▌   | 365/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.12.linear_attn.qkv_proj.MatMul.weight_Q4 (u8, [8192,80,16]):  66%|██████▌   | 366/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.12.linear_attn.qkv_proj.MatMul.weight_scales (f32, [8192,80]):  66%|██████▌   | 367/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.12.linear_attn.z_proj.MatMul.weight_Q4 (u8, [4096,80,16]):  66%|██████▌   | 368/557 [00:00<00:00, 2292.53it/s]    
Saving model.layers.12.linear_attn.z_proj.MatMul.weight_scales (f32, [4096,80]):  66%|██████▌   | 369/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.12.linear_attn.out_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  66%|██████▋   | 370/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.12.linear_attn.out_proj.MatMul.weight_scales (f32, [2560,128]):  67%|██████▋   | 371/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.12.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  67%|██████▋   | 372/557 [00:00<00:00, 2292.53it/s]     
Saving model.layers.12.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  67%|██████▋   | 373/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.12.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  67%|██████▋   | 374/557 [00:00<00:00, 2292.53it/s]      
Saving model.layers.12.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  67%|██████▋   | 375/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.13.linear_attn.qkv_proj.MatMul.weight_Q4 (u8, [8192,80,16]):  68%|██████▊   | 376/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.13.linear_attn.qkv_proj.MatMul.weight_scales (f32, [8192,80]):  68%|██████▊   | 377/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.13.linear_attn.z_proj.MatMul.weight_Q4 (u8, [4096,80,16]):  68%|██████▊   | 378/557 [00:00<00:00, 2292.53it/s]    
Saving model.layers.13.linear_attn.z_proj.MatMul.weight_scales (f32, [4096,80]):  68%|██████▊   | 379/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.13.linear_attn.out_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  68%|██████▊   | 380/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.13.linear_attn.out_proj.MatMul.weight_scales (f32, [2560,128]):  68%|██████▊   | 381/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.13.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  69%|██████▊   | 382/557 [00:00<00:00, 2292.53it/s]     
Saving model.layers.13.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  69%|██████▉   | 383/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.13.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  69%|██████▉   | 384/557 [00:00<00:00, 2292.53it/s]      
Saving model.layers.13.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  69%|██████▉   | 385/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.14.linear_attn.qkv_proj.MatMul.weight_Q4 (u8, [8192,80,16]):  69%|██████▉   | 386/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.14.linear_attn.qkv_proj.MatMul.weight_scales (f32, [8192,80]):  69%|██████▉   | 387/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.14.linear_attn.z_proj.MatMul.weight_Q4 (u8, [4096,80,16]):  70%|██████▉   | 388/557 [00:00<00:00, 2292.53it/s]    
Saving model.layers.14.linear_attn.z_proj.MatMul.weight_scales (f32, [4096,80]):  70%|██████▉   | 389/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.14.linear_attn.out_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  70%|███████   | 390/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.14.linear_attn.out_proj.MatMul.weight_scales (f32, [2560,128]):  70%|███████   | 391/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.14.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  70%|███████   | 392/557 [00:00<00:00, 2292.53it/s]     
Saving model.layers.14.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  71%|███████   | 393/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.14.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  71%|███████   | 394/557 [00:00<00:00, 2292.53it/s]      
Saving model.layers.14.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  71%|███████   | 395/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.15.attn.qkv_proj.MatMul.weight_Q4 (u8, [10240,80,16]):  71%|███████   | 396/557 [00:00<00:00, 2292.53it/s]  
Saving model.layers.15.attn.qkv_proj.MatMul.weight_scales (f32, [10240,80]):  71%|███████▏  | 397/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.15.attn.o_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  71%|███████▏  | 398/557 [00:00<00:00, 2292.53it/s]    
Saving model.layers.15.attn.o_proj.MatMul.weight_scales (f32, [2560,128]):  72%|███████▏  | 399/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.15.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  72%|███████▏  | 400/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.15.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  72%|███████▏  | 401/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.15.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  72%|███████▏  | 402/557 [00:00<00:00, 2292.53it/s]      
Saving model.layers.15.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  72%|███████▏  | 403/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.16.linear_attn.qkv_proj.MatMul.weight_Q4 (u8, [8192,80,16]):  73%|███████▎  | 404/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.16.linear_attn.qkv_proj.MatMul.weight_scales (f32, [8192,80]):  73%|███████▎  | 405/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.16.linear_attn.z_proj.MatMul.weight_Q4 (u8, [4096,80,16]):  73%|███████▎  | 406/557 [00:00<00:00, 2292.53it/s]    
Saving model.layers.16.linear_attn.z_proj.MatMul.weight_scales (f32, [4096,80]):  73%|███████▎  | 407/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.16.linear_attn.out_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  73%|███████▎  | 408/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.16.linear_attn.out_proj.MatMul.weight_scales (f32, [2560,128]):  73%|███████▎  | 409/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.16.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  74%|███████▎  | 410/557 [00:00<00:00, 2292.53it/s]     
Saving model.layers.16.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  74%|███████▍  | 411/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.16.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  74%|███████▍  | 412/557 [00:00<00:00, 2292.53it/s]      
Saving model.layers.16.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  74%|███████▍  | 413/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.17.linear_attn.qkv_proj.MatMul.weight_Q4 (u8, [8192,80,16]):  74%|███████▍  | 414/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.17.linear_attn.qkv_proj.MatMul.weight_scales (f32, [8192,80]):  75%|███████▍  | 415/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.17.linear_attn.z_proj.MatMul.weight_Q4 (u8, [4096,80,16]):  75%|███████▍  | 416/557 [00:00<00:00, 2292.53it/s]    
Saving model.layers.17.linear_attn.z_proj.MatMul.weight_scales (f32, [4096,80]):  75%|███████▍  | 417/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.17.linear_attn.out_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  75%|███████▌  | 418/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.17.linear_attn.out_proj.MatMul.weight_scales (f32, [2560,128]):  75%|███████▌  | 419/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.17.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  75%|███████▌  | 420/557 [00:00<00:00, 2292.53it/s]     
Saving model.layers.17.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  76%|███████▌  | 421/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.17.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  76%|███████▌  | 422/557 [00:00<00:00, 2292.53it/s]      
Saving model.layers.17.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  76%|███████▌  | 423/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.18.linear_attn.qkv_proj.MatMul.weight_Q4 (u8, [8192,80,16]):  76%|███████▌  | 424/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.18.linear_attn.qkv_proj.MatMul.weight_scales (f32, [8192,80]):  76%|███████▋  | 425/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.18.linear_attn.z_proj.MatMul.weight_Q4 (u8, [4096,80,16]):  76%|███████▋  | 426/557 [00:00<00:00, 2292.53it/s]    
Saving model.layers.18.linear_attn.z_proj.MatMul.weight_scales (f32, [4096,80]):  77%|███████▋  | 427/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.18.linear_attn.out_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  77%|███████▋  | 428/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.18.linear_attn.out_proj.MatMul.weight_scales (f32, [2560,128]):  77%|███████▋  | 429/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.18.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  77%|███████▋  | 430/557 [00:00<00:00, 2292.53it/s]     
Saving model.layers.18.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  77%|███████▋  | 431/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.18.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  78%|███████▊  | 432/557 [00:00<00:00, 2292.53it/s]      
Saving model.layers.18.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  78%|███████▊  | 433/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.19.attn.qkv_proj.MatMul.weight_Q4 (u8, [10240,80,16]):  78%|███████▊  | 434/557 [00:00<00:00, 2292.53it/s]  
Saving model.layers.19.attn.qkv_proj.MatMul.weight_scales (f32, [10240,80]):  78%|███████▊  | 435/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.19.attn.o_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  78%|███████▊  | 436/557 [00:00<00:00, 2292.53it/s]    
Saving model.layers.19.attn.o_proj.MatMul.weight_scales (f32, [2560,128]):  78%|███████▊  | 437/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.19.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  79%|███████▊  | 438/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.19.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  79%|███████▉  | 439/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.19.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  79%|███████▉  | 440/557 [00:00<00:00, 2292.53it/s]      
Saving model.layers.19.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  79%|███████▉  | 441/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.20.linear_attn.qkv_proj.MatMul.weight_Q4 (u8, [8192,80,16]):  79%|███████▉  | 442/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.20.linear_attn.qkv_proj.MatMul.weight_scales (f32, [8192,80]):  80%|███████▉  | 443/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.20.linear_attn.z_proj.MatMul.weight_Q4 (u8, [4096,80,16]):  80%|███████▉  | 444/557 [00:00<00:00, 2292.53it/s]    
Saving model.layers.20.linear_attn.z_proj.MatMul.weight_scales (f32, [4096,80]):  80%|███████▉  | 445/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.20.linear_attn.out_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  80%|████████  | 446/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.20.linear_attn.out_proj.MatMul.weight_scales (f32, [2560,128]):  80%|████████  | 447/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.20.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  80%|████████  | 448/557 [00:00<00:00, 2292.53it/s]     
Saving model.layers.20.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  81%|████████  | 449/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.20.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  81%|████████  | 450/557 [00:00<00:00, 2292.53it/s]      
Saving model.layers.20.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  81%|████████  | 451/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.21.linear_attn.qkv_proj.MatMul.weight_Q4 (u8, [8192,80,16]):  81%|████████  | 452/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.21.linear_attn.qkv_proj.MatMul.weight_scales (f32, [8192,80]):  81%|████████▏ | 453/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.21.linear_attn.z_proj.MatMul.weight_Q4 (u8, [4096,80,16]):  82%|████████▏ | 454/557 [00:00<00:00, 2292.53it/s]    
Saving model.layers.21.linear_attn.z_proj.MatMul.weight_scales (f32, [4096,80]):  82%|████████▏ | 455/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.21.linear_attn.out_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  82%|████████▏ | 456/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.21.linear_attn.out_proj.MatMul.weight_scales (f32, [2560,128]):  82%|████████▏ | 457/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.21.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  82%|████████▏ | 458/557 [00:00<00:00, 2292.53it/s]     
Saving model.layers.21.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  82%|████████▏ | 459/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.21.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  83%|████████▎ | 460/557 [00:00<00:00, 2292.53it/s]      
Saving model.layers.21.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  83%|████████▎ | 461/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.22.linear_attn.qkv_proj.MatMul.weight_Q4 (u8, [8192,80,16]):  83%|████████▎ | 462/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.22.linear_attn.qkv_proj.MatMul.weight_scales (f32, [8192,80]):  83%|████████▎ | 463/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.22.linear_attn.z_proj.MatMul.weight_Q4 (u8, [4096,80,16]):  83%|████████▎ | 464/557 [00:00<00:00, 2292.53it/s]    
Saving model.layers.22.linear_attn.z_proj.MatMul.weight_scales (f32, [4096,80]):  83%|████████▎ | 465/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.22.linear_attn.out_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  84%|████████▎ | 466/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.22.linear_attn.out_proj.MatMul.weight_scales (f32, [2560,128]):  84%|████████▍ | 467/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.22.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  84%|████████▍ | 468/557 [00:00<00:00, 2292.53it/s]     
Saving model.layers.22.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  84%|████████▍ | 469/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.22.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  84%|████████▍ | 470/557 [00:00<00:00, 2292.53it/s]      
Saving model.layers.22.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  85%|████████▍ | 471/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.23.attn.qkv_proj.MatMul.weight_Q4 (u8, [10240,80,16]):  85%|████████▍ | 472/557 [00:00<00:00, 2292.53it/s]  
Saving model.layers.23.attn.qkv_proj.MatMul.weight_scales (f32, [10240,80]):  85%|████████▍ | 473/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.23.attn.o_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  85%|████████▌ | 474/557 [00:00<00:00, 2292.53it/s]    
Saving model.layers.23.attn.o_proj.MatMul.weight_scales (f32, [2560,128]):  85%|████████▌ | 475/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.23.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  85%|████████▌ | 476/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.23.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  86%|████████▌ | 477/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.23.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  86%|████████▌ | 478/557 [00:00<00:00, 2292.53it/s]      
Saving model.layers.23.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  86%|████████▌ | 479/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.24.linear_attn.qkv_proj.MatMul.weight_Q4 (u8, [8192,80,16]):  86%|████████▌ | 480/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.24.linear_attn.qkv_proj.MatMul.weight_scales (f32, [8192,80]):  86%|████████▋ | 481/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.24.linear_attn.z_proj.MatMul.weight_Q4 (u8, [4096,80,16]):  87%|████████▋ | 482/557 [00:00<00:00, 2292.53it/s]    
Saving model.layers.24.linear_attn.z_proj.MatMul.weight_scales (f32, [4096,80]):  87%|████████▋ | 483/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.24.linear_attn.out_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  87%|████████▋ | 484/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.24.linear_attn.out_proj.MatMul.weight_scales (f32, [2560,128]):  87%|████████▋ | 485/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.24.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  87%|████████▋ | 486/557 [00:00<00:00, 2292.53it/s]     
Saving model.layers.24.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  87%|████████▋ | 487/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.24.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  88%|████████▊ | 488/557 [00:00<00:00, 2292.53it/s]      
Saving model.layers.24.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  88%|████████▊ | 489/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.25.linear_attn.qkv_proj.MatMul.weight_Q4 (u8, [8192,80,16]):  88%|████████▊ | 490/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.25.linear_attn.qkv_proj.MatMul.weight_scales (f32, [8192,80]):  88%|████████▊ | 491/557 [00:00<00:00, 2292.53it/s]
Saving model.layers.25.linear_attn.qkv_proj.MatMul.weight_scales (f32, [8192,80]):  88%|████████▊ | 492/557 [00:00<00:00, 608.59it/s] 
Saving model.layers.25.linear_attn.z_proj.MatMul.weight_Q4 (u8, [4096,80,16]):  88%|████████▊ | 492/557 [00:00<00:00, 608.59it/s]    
Saving model.layers.25.linear_attn.z_proj.MatMul.weight_scales (f32, [4096,80]):  89%|████████▊ | 493/557 [00:00<00:00, 608.59it/s]
Saving model.layers.25.linear_attn.out_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  89%|████████▊ | 494/557 [00:00<00:00, 608.59it/s]
Saving model.layers.25.linear_attn.out_proj.MatMul.weight_scales (f32, [2560,128]):  89%|████████▉ | 495/557 [00:00<00:00, 608.59it/s]
Saving model.layers.25.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  89%|████████▉ | 496/557 [00:00<00:00, 608.59it/s]     
Saving model.layers.25.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  89%|████████▉ | 497/557 [00:00<00:00, 608.59it/s]
Saving model.layers.25.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  89%|████████▉ | 498/557 [00:00<00:00, 608.59it/s]      
Saving model.layers.25.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  90%|████████▉ | 499/557 [00:00<00:00, 608.59it/s]
Saving model.layers.26.linear_attn.qkv_proj.MatMul.weight_Q4 (u8, [8192,80,16]):  90%|████████▉ | 500/557 [00:00<00:00, 608.59it/s]
Saving model.layers.26.linear_attn.qkv_proj.MatMul.weight_scales (f32, [8192,80]):  90%|████████▉ | 501/557 [00:00<00:00, 608.59it/s]
Saving model.layers.26.linear_attn.z_proj.MatMul.weight_Q4 (u8, [4096,80,16]):  90%|█████████ | 502/557 [00:00<00:00, 608.59it/s]    
Saving model.layers.26.linear_attn.z_proj.MatMul.weight_scales (f32, [4096,80]):  90%|█████████ | 503/557 [00:00<00:00, 608.59it/s]
Saving model.layers.26.linear_attn.out_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  90%|█████████ | 504/557 [00:00<00:00, 608.59it/s]
Saving model.layers.26.linear_attn.out_proj.MatMul.weight_scales (f32, [2560,128]):  91%|█████████ | 505/557 [00:00<00:00, 608.59it/s]
Saving model.layers.26.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  91%|█████████ | 506/557 [00:00<00:00, 608.59it/s]     
Saving model.layers.26.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  91%|█████████ | 507/557 [00:00<00:00, 608.59it/s]
Saving model.layers.26.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  91%|█████████ | 508/557 [00:00<00:00, 608.59it/s]      
Saving model.layers.26.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  91%|█████████▏| 509/557 [00:00<00:00, 608.59it/s]
Saving model.layers.27.attn.qkv_proj.MatMul.weight_Q4 (u8, [10240,80,16]):  92%|█████████▏| 510/557 [00:00<00:00, 608.59it/s]  
Saving model.layers.27.attn.qkv_proj.MatMul.weight_scales (f32, [10240,80]):  92%|█████████▏| 511/557 [00:00<00:00, 608.59it/s]
Saving model.layers.27.attn.o_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  92%|█████████▏| 512/557 [00:00<00:00, 608.59it/s]    
Saving model.layers.27.attn.o_proj.MatMul.weight_scales (f32, [2560,128]):  92%|█████████▏| 513/557 [00:00<00:00, 608.59it/s]
Saving model.layers.27.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  92%|█████████▏| 514/557 [00:00<00:00, 608.59it/s]
Saving model.layers.27.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  92%|█████████▏| 515/557 [00:00<00:00, 608.59it/s]
Saving model.layers.27.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  93%|█████████▎| 516/557 [00:00<00:00, 608.59it/s]      
Saving model.layers.27.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  93%|█████████▎| 517/557 [00:00<00:00, 608.59it/s]
Saving model.layers.28.linear_attn.qkv_proj.MatMul.weight_Q4 (u8, [8192,80,16]):  93%|█████████▎| 518/557 [00:00<00:00, 608.59it/s]
Saving model.layers.28.linear_attn.qkv_proj.MatMul.weight_scales (f32, [8192,80]):  93%|█████████▎| 519/557 [00:00<00:00, 608.59it/s]
Saving model.layers.28.linear_attn.z_proj.MatMul.weight_Q4 (u8, [4096,80,16]):  93%|█████████▎| 520/557 [00:00<00:00, 608.59it/s]    
Saving model.layers.28.linear_attn.z_proj.MatMul.weight_scales (f32, [4096,80]):  94%|█████████▎| 521/557 [00:00<00:00, 608.59it/s]
Saving model.layers.28.linear_attn.out_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  94%|█████████▎| 522/557 [00:00<00:00, 608.59it/s]
Saving model.layers.28.linear_attn.out_proj.MatMul.weight_scales (f32, [2560,128]):  94%|█████████▍| 523/557 [00:00<00:00, 608.59it/s]
Saving model.layers.28.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  94%|█████████▍| 524/557 [00:00<00:00, 608.59it/s]     
Saving model.layers.28.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  94%|█████████▍| 525/557 [00:00<00:00, 608.59it/s]
Saving model.layers.28.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  94%|█████████▍| 526/557 [00:00<00:00, 608.59it/s]      
Saving model.layers.28.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  95%|█████████▍| 527/557 [00:00<00:00, 608.59it/s]
Saving model.layers.29.linear_attn.qkv_proj.MatMul.weight_Q4 (u8, [8192,80,16]):  95%|█████████▍| 528/557 [00:00<00:00, 608.59it/s]
Saving model.layers.29.linear_attn.qkv_proj.MatMul.weight_scales (f32, [8192,80]):  95%|█████████▍| 529/557 [00:00<00:00, 608.59it/s]
Saving model.layers.29.linear_attn.z_proj.MatMul.weight_Q4 (u8, [4096,80,16]):  95%|█████████▌| 530/557 [00:00<00:00, 608.59it/s]    
Saving model.layers.29.linear_attn.z_proj.MatMul.weight_scales (f32, [4096,80]):  95%|█████████▌| 531/557 [00:00<00:00, 608.59it/s]
Saving model.layers.29.linear_attn.out_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  96%|█████████▌| 532/557 [00:00<00:00, 608.59it/s]
Saving model.layers.29.linear_attn.out_proj.MatMul.weight_scales (f32, [2560,128]):  96%|█████████▌| 533/557 [00:00<00:00, 608.59it/s]
Saving model.layers.29.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  96%|█████████▌| 534/557 [00:00<00:00, 608.59it/s]     
Saving model.layers.29.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  96%|█████████▌| 535/557 [00:00<00:00, 608.59it/s]
Saving model.layers.29.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  96%|█████████▌| 536/557 [00:00<00:00, 608.59it/s]      
Saving model.layers.29.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  96%|█████████▋| 537/557 [00:00<00:00, 608.59it/s]
Saving model.layers.30.linear_attn.qkv_proj.MatMul.weight_Q4 (u8, [8192,80,16]):  97%|█████████▋| 538/557 [00:00<00:00, 608.59it/s]
Saving model.layers.30.linear_attn.qkv_proj.MatMul.weight_scales (f32, [8192,80]):  97%|█████████▋| 539/557 [00:00<00:00, 608.59it/s]
Saving model.layers.30.linear_attn.z_proj.MatMul.weight_Q4 (u8, [4096,80,16]):  97%|█████████▋| 540/557 [00:00<00:00, 608.59it/s]    
Saving model.layers.30.linear_attn.z_proj.MatMul.weight_scales (f32, [4096,80]):  97%|█████████▋| 541/557 [00:00<00:00, 608.59it/s]
Saving model.layers.30.linear_attn.out_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  97%|█████████▋| 542/557 [00:00<00:00, 608.59it/s]
Saving model.layers.30.linear_attn.out_proj.MatMul.weight_scales (f32, [2560,128]):  97%|█████████▋| 543/557 [00:00<00:00, 608.59it/s]
Saving model.layers.30.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  98%|█████████▊| 544/557 [00:00<00:00, 608.59it/s]     
Saving model.layers.30.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  98%|█████████▊| 545/557 [00:00<00:00, 608.59it/s]
Saving model.layers.30.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  98%|█████████▊| 546/557 [00:00<00:00, 608.59it/s]      
Saving model.layers.30.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  98%|█████████▊| 547/557 [00:00<00:00, 608.59it/s]
Saving model.layers.31.attn.qkv_proj.MatMul.weight_Q4 (u8, [10240,80,16]):  98%|█████████▊| 548/557 [00:00<00:00, 608.59it/s]  
Saving model.layers.31.attn.qkv_proj.MatMul.weight_scales (f32, [10240,80]):  99%|█████████▊| 549/557 [00:00<00:00, 608.59it/s]
Saving model.layers.31.attn.o_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  99%|█████████▊| 550/557 [00:00<00:00, 608.59it/s]    
Saving model.layers.31.attn.o_proj.MatMul.weight_scales (f32, [2560,128]):  99%|█████████▉| 551/557 [00:00<00:00, 608.59it/s]
Saving model.layers.31.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  99%|█████████▉| 552/557 [00:00<00:00, 608.59it/s]
Saving model.layers.31.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  99%|█████████▉| 553/557 [00:00<00:00, 608.59it/s]
Saving model.layers.31.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  99%|█████████▉| 554/557 [00:00<00:00, 608.59it/s]      
Saving model.layers.31.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]): 100%|█████████▉| 555/557 [00:00<00:00, 608.59it/s]
Saving lm_head.MatMul.weight_Q4 (u8, [248320,80,16]): 100%|█████████▉| 556/557 [00:00<00:00, 608.59it/s]                       
Saving lm_head.MatMul.weight_scales (f32, [248320,80]): 100%|██████████| 557/557 [00:01<00:00, 608.59it/s]
Saving lm_head.MatMul.weight_scales (f32, [248320,80]): 100%|██████████| 557/557 [00:01<00:00, 503.27it/s]
2026-11-05 03:43:03,790 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/constant_nodes/INT64/[1] ...
2026-11-05 03:43:03,790 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/attn_mask_reformat/attn_mask_subgraph/ReduceSum ...
2026-11-05 03:43:03,790 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/attn_mask_reformat/attn_mask_subgraph/Sub ...
2026-11-05 03:43:03,790 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/attn_mask_reformat/attn_mask_subgraph/Sub/Cast ...
2026-11-05 03:43:03,790 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/attn_mask_reformat/attn_mask_subgraph/Shape ...
2026-11-05 03:43:03,790 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/constant_nodes/INT64/1 ...
2026-11-05 03:43:03,790 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/attn_mask_reformat/attn_mask_subgraph/Gather ...
2026-11-05 03:43:03,790 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - Gather doesn't have const weight. Skip quantization.
2026-11-05 03:43:03,790 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/attn_mask_reformat/attn_mask_subgraph/Gather with 4 bits ...
2026-11-05 03:43:03,790 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/attn_mask_reformat/attn_mask_subgraph/Gather/Cast ...
2026-11-05 03:43:03,790 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/constant_nodes/INT64/[248320, 1280] ...
2026-11-05 03:43:03,790 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/mtp/embed_tokens/Reshape ...
2026-11-05 03:43:03,790 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/mtp/embed_tokens/GatherBlockQuantized ...
2026-11-05 03:43:03,790 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/mtp/pre_fc_norm_embedding ...
2026-11-05 03:43:03,790 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/mtp/pre_fc_norm_hidden ...
2026-11-05 03:43:03,790 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/mtp/fc/Concat ...
2026-11-05 03:43:03,790 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/mtp/fc/MatMul ...
2026-11-05 03:43:03,823 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/mtp/fc/MatMul with 4 bits ...
2026-11-05 03:43:03,823 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/input_layernorm/LayerNorm ...
2026-11-05 03:43:03,823 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.0/attn/qkv_proj/MatMul ...
2026-11-05 03:43:03,870 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.0/attn/qkv_proj/MatMul with 4 bits ...
2026-11-05 03:43:03,870 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/constant_nodes/INT64/[8192, 1024, 1024] ...
2026-11-05 03:43:03,870 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/attn/qkv_proj/Split ...
2026-11-05 03:43:03,870 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/constant_nodes/INT64/[0, 0, 16, 512] ...
2026-11-05 03:43:03,870 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/attn/q_gate/Reshape ...
2026-11-05 03:43:03,870 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/constant_nodes/INT64/[256, 256] ...
2026-11-05 03:43:03,870 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/attn/q_gate/Split ...
2026-11-05 03:43:03,871 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/constant_nodes/INT64/[0, 0, 4096] ...
2026-11-05 03:43:03,871 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/attn/q_proj/Reshape ...
2026-11-05 03:43:03,871 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/attn/gate/Reshape ...
2026-11-05 03:43:03,871 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/constant_nodes/INT64/[0, -1, 256] ...
2026-11-05 03:43:03,871 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/attn/q_norm/Reshape_1 ...
2026-11-05 03:43:03,871 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/attn/q_norm/SimplifiedLayerNormalization ...
2026-11-05 03:43:03,871 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/constant_nodes/INT64/[0, -1, 4096] ...
2026-11-05 03:43:03,871 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/attn/q_norm/Reshape_2 ...
2026-11-05 03:43:03,871 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/attn/k_norm/Reshape_1 ...
2026-11-05 03:43:03,871 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/attn/k_norm/SimplifiedLayerNormalization ...
2026-11-05 03:43:03,871 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/constant_nodes/INT64/[0, -1, 1024] ...
2026-11-05 03:43:03,871 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/attn/k_norm/Reshape_2 ...
2026-11-05 03:43:03,871 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/attn/q_rotary/MRotaryEmbedding ...
2026-11-05 03:43:03,871 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/attn/k_rotary/MRotaryEmbedding ...
2026-11-05 03:43:03,871 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/attn/GroupQueryAttention ...
2026-11-05 03:43:03,871 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/attn/gate/Sigmoid ...
2026-11-05 03:43:03,871 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/attn/gate/Mul ...
2026-11-05 03:43:03,871 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.0/attn/o_proj/MatMul ...
2026-11-05 03:43:03,896 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.0/attn/o_proj/MatMul with 4 bits ...
2026-11-05 03:43:03,896 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/post_attention_layernorm/SkipLayerNorm ...
2026-11-05 03:43:03,896 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.0/mlp/gate_up_proj/MatMul ...
2026-11-05 03:43:04,022 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.0/mlp/gate_up_proj/MatMul with 4 bits ...
2026-11-05 03:43:04,022 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/mlp/gate_up_proj/Split ...
2026-11-05 03:43:04,022 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/mlp/act_fn/Sigmoid ...
2026-11-05 03:43:04,022 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/mlp/act_fn/Mul ...
2026-11-05 03:43:04,022 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.0/mlp/Mul ...
2026-11-05 03:43:04,022 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /model/layers.0/mlp/down_proj/MatMul ...
2026-11-05 03:43:04,070 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /model/layers.0/mlp/down_proj/MatMul with 4 bits ...
2026-11-05 03:43:04,070 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - skip to quantize /model/layers.1/final_norm_layernorm/SkipLayerNorm ...
2026-11-05 03:43:04,070 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - start to quantize /lm_head/MatMul ...
2026-11-05 03:43:06,450 onnxruntime.quantization.matmul_nbits_quantizer [INFO] - complete quantization of /lm_head/MatMul with 4 bits ...
Saving ONNX model in /home/anon/knowline/onnx/model-cpu

0it [00:00, ?it/s]
Saving model.mtp.pre_fc_norm_embedding.weight (f32, [2560]):   5%|▍         | 1/21 [00:00<00:00, 735.46it/s]
Saving model.mtp.pre_fc_norm_hidden.weight (f32, [2560]):  10%|▉         | 2/21 [00:00<00:00, 1372.71it/s]  
Saving model.layers.0.input_layernorm.weight (f32, [2560]):  14%|█▍        | 3/21 [00:00<00:00, 1997.92it/s]
Saving model.layers.0.attn.q_norm.layernorm.weight (f32, [256]):  19%|█▉        | 4/21 [00:00<00:00, 2603.94it/s]
Saving model.layers.0.attn.k_norm.layernorm.weight (f32, [256]):  24%|██▍       | 5/21 [00:00<00:00, 3199.80it/s]
Saving cos_cache (f32, [262144,32]):  29%|██▊       | 6/21 [00:00<00:00, 3772.99it/s]                            
Saving sin_cache (f32, [262144,32]):  33%|███▎      | 7/21 [00:00<00:00, 1170.66it/s]
Saving model.layers.0.post_attention_layernorm.weight (f32, [2560]):  38%|███▊      | 8/21 [00:00<00:00, 758.81it/s]
Saving model.layers.1.final_norm_layernorm.weight (f32, [2560]):  43%|████▎     | 9/21 [00:00<00:00, 845.23it/s]    
Saving model.mtp.fc.MatMul.weight_Q4 (u8, [2560,160,16]):  48%|████▊     | 10/21 [00:00<00:00, 935.04it/s]      
Saving model.mtp.fc.MatMul.weight_scales (f32, [2560,160]):  52%|█████▏    | 11/21 [00:00<00:00, 953.27it/s]
Saving model.layers.0.attn.qkv_proj.MatMul.weight_Q4 (u8, [10240,80,16]):  57%|█████▋    | 12/21 [00:00<00:00, 1019.48it/s]
Saving model.layers.0.attn.qkv_proj.MatMul.weight_scales (f32, [10240,80]):  62%|██████▏   | 13/21 [00:00<00:00, 961.08it/s]
Saving model.layers.0.attn.o_proj.MatMul.weight_Q4 (u8, [2560,128,16]):  67%|██████▋   | 14/21 [00:00<00:00, 986.23it/s]    
Saving model.layers.0.attn.o_proj.MatMul.weight_scales (f32, [2560,128]):  71%|███████▏  | 15/21 [00:00<00:00, 1003.15it/s]
Saving model.layers.0.mlp.gate_up_proj.MatMul.input_1_Q4 (u8, [18432,80,16]):  76%|███████▌  | 16/21 [00:00<00:00, 1055.02it/s]
Saving model.layers.0.mlp.gate_up_proj.MatMul.input_1_scales (f32, [18432,80]):  81%|████████  | 17/21 [00:00<00:00, 932.48it/s]
Saving model.layers.0.mlp.down_proj.MatMul.weight_Q4 (u8, [2560,288,16]):  86%|████████▌ | 18/21 [00:00<00:00, 946.45it/s]      
Saving model.layers.0.mlp.down_proj.MatMul.weight_scales (f32, [2560,288]):  90%|█████████ | 19/21 [00:00<00:00, 915.77it/s]
Saving lm_head.MatMul.weight_Q4 (u8, [248320,80,16]):  95%|█████████▌| 20/21 [00:00<00:00, 945.72it/s]                      
Saving lm_head.MatMul.weight_Q4 (u8, [248320,80,16]): 100%|██████████| 21/21 [00:00<00:00, 131.28it/s]
Saving lm_head.MatMul.weight_scales (f32, [248320,80]): 100%|██████████| 21/21 [00:00<00:00, 131.28it/s]
Saving lm_head.MatMul.weight_scales (f32, [248320,80]): 100%|██████████| 21/21 [00:00<00:00, 114.16it/s]
Configured 397 MB of runtime initializer sharing; /home/anon/knowline/onnx/model-cpu/mtp.onnx.data remains self-contained.
Warning: could not read generation_config.json (/home/anon/LLM/KnowLine-4B-Gen5.5 does not appear to have a file named generation_config.json. Checkout 'https://huggingface.co//home/anon/LLM/KnowLine-4B-Gen5.5/tree/main' for available files.). Falling back to config.json.
Adding the tokenizer's end-of-turn token <|im_end|> (id 248046) to eos_token_id from the model configuration: 248044.
Saving GenAI config in /home/anon/knowline/onnx/model-cpu
Added 'mtp' section to genai_config.json
Saving processing files in /home/anon/knowline/onnx/model-cpu for GenAI
EXIT:0