aboutsummaryrefslogtreecommitdiff
path: root/ggml-metal.m
blob: fd69c41fe357d6e1636f2640186c7908352450b9 (plain)
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
#import "ggml-metal.h"

#import "ggml.h"

#import <Foundation/Foundation.h>

#import <Metal/Metal.h>
#import <MetalPerformanceShaders/MetalPerformanceShaders.h>

#ifdef GGML_METAL_NDEBUG
#define metal_printf(...)
#else
#define metal_printf(...) fprintf(stderr, __VA_ARGS__)
#endif

#define UNUSED(x) (void)(x)

struct ggml_metal_buffer {
    const char * name;

    void   * data;
    size_t   size;

    id<MTLBuffer> metal;
};

struct ggml_metal_context {
    float * logits;

    id<MTLDevice>       device;
    id<MTLCommandQueue> queue;
    id<MTLLibrary>      library;

    int n_buffers;
    struct ggml_metal_buffer buffers[GGML_METAL_MAX_BUFFERS];

    // custom kernels
#define GGML_METAL_DECL_KERNEL(name) \
    id<MTLFunction>             function_##name; \
    id<MTLComputePipelineState> pipeline_##name

    GGML_METAL_DECL_KERNEL(add);
    GGML_METAL_DECL_KERNEL(mul);
    GGML_METAL_DECL_KERNEL(mul_row); // TODO: avoid this extra kernel, instead extend the "mul" kernel to support broadcast
    GGML_METAL_DECL_KERNEL(scale);
    GGML_METAL_DECL_KERNEL(silu);
    GGML_METAL_DECL_KERNEL(relu);
    GGML_METAL_DECL_KERNEL(gelu);
    GGML_METAL_DECL_KERNEL(soft_max);
    GGML_METAL_DECL_KERNEL(diag_mask_inf);
    GGML_METAL_DECL_KERNEL(get_rows_f16);
    GGML_METAL_DECL_KERNEL(get_rows_q4_0);
    GGML_METAL_DECL_KERNEL(get_rows_q4_1);
    GGML_METAL_DECL_KERNEL(get_rows_q2_K);
    GGML_METAL_DECL_KERNEL(get_rows_q3_K);
    GGML_METAL_DECL_KERNEL(get_rows_q4_K);
    GGML_METAL_DECL_KERNEL(get_rows_q5_K);
    GGML_METAL_DECL_KERNEL(get_rows_q6_K);
    GGML_METAL_DECL_KERNEL(rms_norm);
    GGML_METAL_DECL_KERNEL(norm);
    GGML_METAL_DECL_KERNEL(mul_mat_f16_f32);
    GGML_METAL_DECL_KERNEL(mul_mat_q4_0_f32);
    GGML_METAL_DECL_KERNEL(mul_mat_q4_1_f32);
    GGML_METAL_DECL_KERNEL(mul_mat_q2_K_f32);
    GGML_METAL_DECL_KERNEL(mul_mat_q3_K_f32);
    GGML_METAL_DECL_KERNEL(mul_mat_q4_K_f32);
    GGML_METAL_DECL_KERNEL(mul_mat_q5_K_f32);
    GGML_METAL_DECL_KERNEL(mul_mat_q6_K_f32);
    GGML_METAL_DECL_KERNEL(rope);
    GGML_METAL_DECL_KERNEL(alibi_f32);
    GGML_METAL_DECL_KERNEL(cpy_f32_f16);
    GGML_METAL_DECL_KERNEL(cpy_f32_f32);
    GGML_METAL_DECL_KERNEL(cpy_f16_f16);

#undef GGML_METAL_DECL_KERNEL
};

// MSL code
// TODO: move the contents here when ready
//       for now it is easier to work in a separate file
static NSString * const msl_library_source = @"see metal.metal";

// Here to assist with NSBundle Path Hack
@interface GGMLMetalClass : NSObject
@end
@implementation GGMLMetalClass
@end

struct ggml_metal_context * ggml_metal_init(void) {
    fprintf(stderr, "%s: allocating\n", __func__);

    struct ggml_metal_context * ctx = malloc(sizeof(struct ggml_metal_context));

    ctx->device = MTLCreateSystemDefaultDevice();
    ctx->queue  = [ctx->device newCommandQueue];
    ctx->n_buffers = 0;

    // determine if we can use MPS
    if (MPSSupportsMTLDevice(ctx->device)) {
        fprintf(stderr, "%s: using MPS\n", __func__);
    } else {
        fprintf(stderr, "%s: not using MPS\n", __func__);
        GGML_ASSERT(false && "MPS not supported");
    }

#if 0
    // compile from source string and show compile log
    {
        NSError * error = nil;

        ctx->library = [ctx->device newLibraryWithSource:msl_library_source options:nil error:&error];
        if (error) {
            fprintf(stderr, "%s: error: %s\n", __func__, [[error description] UTF8String]);
            exit(1);
        }
    }
#else
    UNUSED(msl_library_source);

    // read the source from "ggml-metal.metal" into a string and use newLibraryWithSource
    {
        NSError * error = nil;

        //NSString * path = [[NSBundle mainBundle] pathForResource:@"../../examples/metal/metal" ofType:@"metal"];
        NSBundle * bundle = [NSBundle bundleForClass:[GGMLMetalClass class]];
        NSString * path = [bundle pathForResource:@"ggml-metal" ofType:@"metal"];
        fprintf(stderr, "%s: loading '%s'\n", __func__, [path UTF8String]);

        NSString * src  = [NSString stringWithContentsOfFile:path encoding:NSUTF8StringEncoding error:&error];
        if (error) {
            fprintf(stderr, "%s: error: %s\n", __func__, [[error description] UTF8String]);
            exit(1);
        }

#ifdef GGML_QKK_64
        MTLCompileOptions* options = [MTLCompileOptions new];
        options.preprocessorMacros = @{ @"QK_K" : @(64) };
        ctx->library = [ctx->device newLibraryWithSource:src options:options error:&error];
#else
        ctx->library = [ctx->device newLibraryWithSource:src options:nil error:&error];
#endif
        if (error) {
            fprintf(stderr, "%s: error: %s\n", __func__, [[error description] UTF8String]);
            exit(1);
        }
    }
#endif

    // load kernels
    {
#define GGML_METAL_ADD_KERNEL(name) \
        ctx->function_##name = [ctx->library newFunctionWithName:@"kernel_"#name]; \
        ctx->pipeline_##name = [ctx->device newComputePipelineStateWithFunction:ctx->function_##name error:nil]; \
        fprintf(stderr, "%s: loaded %-32s %16p\n", __func__, "kernel_"#name, (void *) ctx->pipeline_##name);

        GGML_METAL_ADD_KERNEL(add);
        GGML_METAL_ADD_KERNEL(mul);
        GGML_METAL_ADD_KERNEL(mul_row);
        GGML_METAL_ADD_KERNEL(scale);
        GGML_METAL_ADD_KERNEL(silu);
        GGML_METAL_ADD_KERNEL(relu);
        GGML_METAL_ADD_KERNEL(gelu);
        GGML_METAL_ADD_KERNEL(soft_max);
        GGML_METAL_ADD_KERNEL(diag_mask_inf);
        GGML_METAL_ADD_KERNEL(get_rows_f16);
        GGML_METAL_ADD_KERNEL(get_rows_q4_0);
        GGML_METAL_ADD_KERNEL(get_rows_q4_1);
        GGML_METAL_ADD_KERNEL(get_rows_q2_K);
        GGML_METAL_ADD_KERNEL(get_rows_q3_K);
        GGML_METAL_ADD_KERNEL(get_rows_q4_K);
        GGML_METAL_ADD_KERNEL(get_rows_q5_K);
        GGML_METAL_ADD_KERNEL(get_rows_q6_K);
        GGML_METAL_ADD_KERNEL(rms_norm);
        GGML_METAL_ADD_KERNEL(norm);
        GGML_METAL_ADD_KERNEL(mul_mat_f16_f32);
        GGML_METAL_ADD_KERNEL(mul_mat_q4_0_f32);
        GGML_METAL_ADD_KERNEL(mul_mat_q4_1_f32);
        GGML_METAL_ADD_KERNEL(mul_mat_q2_K_f32);
        GGML_METAL_ADD_KERNEL(mul_mat_q3_K_f32);
        GGML_METAL_ADD_KERNEL(mul_mat_q4_K_f32);
        GGML_METAL_ADD_KERNEL(mul_mat_q5_K_f32);
        GGML_METAL_ADD_KERNEL(mul_mat_q6_K_f32);
        GGML_METAL_ADD_KERNEL(rope);
        GGML_METAL_ADD_KERNEL(alibi_f32);
        GGML_METAL_ADD_KERNEL(cpy_f32_f16);
        GGML_METAL_ADD_KERNEL(cpy_f32_f32);
        GGML_METAL_ADD_KERNEL(cpy_f16_f16);

#undef GGML_METAL_ADD_KERNEL
    }

    fprintf(stderr, "%s: recommendedMaxWorkingSetSize = %8.2f MB\n", __func__, ctx->device.recommendedMaxWorkingSetSize / 1024.0 / 1024.0);
    fprintf(stderr, "%s: hasUnifiedMemory             = %s\n",       __func__, ctx->device.hasUnifiedMemory ? "true" : "false");
    if (ctx->device.maxTransferRate != 0) {
        fprintf(stderr, "%s: maxTransferRate              = %8.2f MB/s\n", __func__, ctx->device.maxTransferRate / 1024.0 / 1024.0);
    } else {
        fprintf(stderr, "%s: maxTransferRate              = built-in GPU\n", __func__);
    }

    return ctx;
}

void ggml_metal_free(struct ggml_metal_context * ctx) {
    fprintf(stderr, "%s: deallocating\n", __func__);
    for (int i = 0; i < ctx->n_buffers; ++i) {
        [ctx->buffers[i].metal release];
    }
    free(ctx);
}

// finds the Metal buffer that contains the tensor data on the GPU device
// the assumption is that there is 1-to-1 mapping between the host and device memory buffers, so we can find the
// Metal buffer based on the host memory pointer
//
static id<MTLBuffer> ggml_metal_get_buffer(struct ggml_metal_context * ctx, struct ggml_tensor * t, size_t * offs) {
    //fprintf(stderr, "%s: data tensor '%16s', offs_data = %8ld, offs_eval = %8ld, offs_cach = %8ld\n", __func__, t->name, offs_data, offs_eval, offs_cach);

    const int64_t tsize = ggml_nbytes(t);

    // find the view that contains the tensor fully
    for (int i = 0; i < ctx->n_buffers; ++i) {
        const int64_t ioffs = (int64_t) t->data - (int64_t) ctx->buffers[i].data;

        if (ioffs >= 0 && ioffs + tsize <= (int64_t) ctx->buffers[i].size) {
            *offs = (size_t) ioffs;

            //fprintf(stderr, "%s: '%s' tensor '%16s', offs = %8ld\n", __func__, ctx->buffers[i].name, t->name, *offs);

            return ctx->buffers[i].metal;
        }
    }

    fprintf(stderr, "%s: error: buffer is nil\n", __func__);

    return nil;
}

bool ggml_metal_add_buffer(
        struct ggml_metal_context * ctx,
                     const char * name,
                           void * data,
                         size_t   size,
                         size_t   max_size) {
    if (ctx->n_buffers >= GGML_METAL_MAX_BUFFERS) {
        fprintf(stderr, "%s: too many buffers\n", __func__);
        return false;
    }

    if (data) {
        // verify that the buffer does not overlap with any of the existing buffers
        for (int i = 0; i < ctx->n_buffers; ++i) {
            const int64_t ioffs = (int64_t) data - (int64_t) ctx->buffers[i].data;

            if (ioffs >= 0 && ioffs < (int64_t) ctx->buffers[i].size) {
                fprintf(stderr, "%s: error: buffer '%s' overlaps with '%s'\n", __func__, name, ctx->buffers[i].name);
                return false;
            }
        }

        const size_t size_page = getpagesize();

        size_t size_aligned = size;
        if ((size_aligned % size_page) != 0) {
            size_aligned += (size_page - (size_aligned % size_page));
        }

        // the buffer fits into the max buffer size allowed by the device
        if (size_aligned <= ctx->device.maxBufferLength) {
            ctx->buffers[ctx->n_buffers].name = name;
            ctx->buffers[ctx->n_buffers].data = data;
            ctx->buffers[ctx->n_buffers].size = size;

            ctx->buffers[ctx->n_buffers].metal = [ctx->device newBufferWithBytesNoCopy:data length:size_aligned options:MTLResourceStorageModeShared deallocator:nil];

            if (ctx->buffers[ctx->n_buffers].metal == nil) {
                fprintf(stderr, "%s: failed to allocate '%-16s' buffer, size = %8.2f MB\n", __func__, name, size_aligned / 1024.0 / 1024.0);
                return false;
            }

            fprintf(stderr, "%s: allocated '%-16s' buffer, size = %8.2f MB", __func__, name, size_aligned / 1024.0 / 1024.0);

            ++ctx->n_buffers;
        } else {
            // this overlap between the views will guarantee that the tensor with the maximum size will fully fit into
            // one of the views
            const size_t size_ovlp = ((max_size + size_page - 1) / size_page + 1) * size_page; // round-up 2 pages just in case
            const size_t size_step = ctx->device.maxBufferLength - size_ovlp;
            const size_t size_view = ctx->device.maxBufferLength;

            for (size_t i = 0; i < size; i += size_step) {
                const size_t size_step_aligned = (i + size_view <= size) ? size_view : (size_aligned - i);

                ctx->buffers[ctx->n_buffers].name = name;
                ctx->buffers[ctx->n_buffers].data = (void *) ((uint8_t *) data + i);
                ctx->buffers[ctx->n_buffers].size = size_step_aligned;

                ctx->buffers[ctx->n_buffers].metal = [ctx->device newBufferWithBytesNoCopy:(void *) ((uint8_t *) data + i) length:size_step_aligned options:MTLResourceStorageModeShared deallocator:nil];

                if (ctx->buffers[ctx->n_buffers].metal == nil) {
                    fprintf(stderr, "%s: failed to allocate '%-16s' buffer, size = %8.2f MB\n", __func__, name, size_step_aligned / 1024.0 / 1024.0);
                    return false;
                }

                fprintf(stderr, "%s: allocated '%-16s' buffer, size = %8.2f MB, offs = %12ld", __func__, name, size_step_aligned / 1024.0 / 1024.0, i);
                if (i + size_step < size) {
                    fprintf(stderr, "\n");
                }

                ++ctx->n_buffers;
            }
        }

        fprintf(stderr, ", (%8.2f / %8.2f)",
                ctx->device.currentAllocatedSize / 1024.0 / 1024.0,
                ctx->device.recommendedMaxWorkingSetSize / 1024.0 / 1024.0);

        if (ctx->device.currentAllocatedSize > ctx->device.recommendedMaxWorkingSetSize) {
            fprintf(stderr, ", warning: current allocated size is greater than the recommended max working set size\n");
        } else {
            fprintf(stderr, "\n");
        }
    }

    return true;
}

void ggml_metal_set_tensor(
        struct ggml_metal_context * ctx,
        struct ggml_tensor * t) {
    metal_printf("%s: set input for tensor '%s'\n", __func__, t->name);

    size_t offs;
    id<MTLBuffer> id_dst = ggml_metal_get_buffer(ctx, t, &offs);

    memcpy((void *) ((uint8_t *) id_dst.contents + offs), t->data, ggml_nbytes(t));
}

void ggml_metal_get_tensor(
        struct ggml_metal_context * ctx,
        struct ggml_tensor * t) {
    metal_printf("%s: extract results for tensor '%s'\n", __func__, t->name);

    size_t offs;
    id<MTLBuffer> id_src = ggml_metal_get_buffer(ctx, t, &offs);

    memcpy(t->data, (void *) ((uint8_t *) id_src.contents + offs), ggml_nbytes(t));
}

void ggml_metal_graph_compute(
        struct ggml_metal_context * ctx,
               struct ggml_cgraph * gf) {
    metal_printf("%s: evaluating graph\n", __func__);

    // create multiple command buffers and enqueue them
    // then, we encode the graph into the command buffers in parallel

    const int n_cb = gf->n_threads;

    NSMutableArray * command_buffers = [NSMutableArray arrayWithCapacity:n_cb];

    for (int i = 0; i < n_cb; ++i) {
        command_buffers[i] = [ctx->queue commandBuffer];

        // enqueue the command buffers in order to specify their execution order
        [command_buffers[i] enqueue];
    }

    // TODO: is this the best way to start threads?
    dispatch_queue_t queue = dispatch_queue_create("llama.cpp", DISPATCH_QUEUE_CONCURRENT);

    for (int cb_idx = 0; cb_idx < n_cb; ++cb_idx) {
        const int n_nodes_per_cb = (gf->n_nodes + n_cb - 1) / n_cb;

        dispatch_async(queue, ^{
            size_t offs_src0 = 0;
            size_t offs_src1 = 0;
            size_t offs_dst  = 0;

            id<MTLCommandBuffer> command_buffer = command_buffers[cb_idx];

            id<MTLComputeCommandEncoder> encoder = nil;

            const int node_start =                                      (cb_idx + 0) * n_nodes_per_cb;
            const int node_end   = (cb_idx == n_cb - 1) ? gf->n_nodes : (cb_idx + 1) * n_nodes_per_cb;

            for (int i = node_start; i < node_end; ++i) {
                metal_printf("%s: encoding node %3d, op = %8s\n", __func__, i, ggml_op_name(gf->nodes[i]->op));

                struct ggml_tensor * src0 = gf->nodes[i]->src0;
                struct ggml_tensor * src1 = gf->nodes[i]->src1;
                struct ggml_tensor * dst  = gf->nodes[i];

                const int64_t  ne00 = src0 ? src0->ne[0] : 0;
                const int64_t  ne01 = src0 ? src0->ne[1] : 0;
                const int64_t  ne02 = src0 ? src0->ne[2] : 0;
                const int64_t  ne03 = src0 ? src0->ne[3] : 0;

                const uint64_t nb00 = src0 ? src0->nb[0] : 0;
                const uint64_t nb01 = src0 ? src0->nb[1] : 0;
                const uint64_t nb02 = src0 ? src0->nb[2] : 0;
                const uint64_t nb03 = src0 ? src0->nb[3] : 0;

                const int64_t  ne10 = src1 ? src1->ne[0] : 0;
                const int64_t  ne11 = src1 ? src1->ne[1] : 0;
                const int64_t  ne12 = src1 ? src1->ne[2] : 0;
                const int64_t  ne13 = src1 ? src1->ne[3] : 0; UNUSED(ne13);

                const uint64_t nb10 = src1 ? src1->nb[0] : 0;
                const uint64_t nb11 = src1 ? src1->nb[1] : 0;
                const uint64_t nb12 = src1 ? src1->nb[2] : 0;
                const uint64_t nb13 = src1 ? src1->nb[3] : 0; UNUSED(nb13);

                const int64_t  ne0  = dst ? dst->ne[0] : 0;
                const int64_t  ne1  = dst ? dst->ne[1] : 0;
                const int64_t  ne2  = dst ? dst->ne[2] : 0;
                const int64_t  ne3  = dst ? dst->ne[3] : 0;

                const uint64_t nb0  = dst ? dst->nb[0] : 0;
                const uint64_t nb1  = dst ? dst->nb[1] : 0;
                const uint64_t nb2  = dst ? dst->nb[2] : 0;
                const uint64_t nb3  = dst ? dst->nb[3] : 0;

                const enum ggml_type src0t = src0 ? src0->type : GGML_TYPE_COUNT;
                const enum ggml_type src1t = src1 ? src1->type : GGML_TYPE_COUNT;
                const enum ggml_type dstt  = dst  ? dst->type  : GGML_TYPE_COUNT;

                id<MTLBuffer> id_src0 = src0 ? ggml_metal_get_buffer(ctx, src0, &offs_src0) : nil;
                id<MTLBuffer> id_src1 = src1 ? ggml_metal_get_buffer(ctx, src1, &offs_src1) : nil;
                id<MTLBuffer> id_dst  = dst  ? ggml_metal_get_buffer(ctx, dst,  &offs_dst)  : nil;

                //metal_printf("%s: op - %s\n", __func__, ggml_op_name(dst->op));
                //if (src0) {
                //    metal_printf("%s: src0 - %4s [%5lld, %5lld, %5lld], %d, %s\n", __func__, ggml_type_name(src0t), ne00, ne01, ne02,
                //            ggml_is_contiguous(src0), src0->name);
                //}
                //if (src1) {
                //    metal_printf("%s: src1 - %4s [%5lld, %5lld, %5lld], %d, %s\n", __func__, ggml_type_name(src1t), ne10, ne11, ne12,
                //            ggml_is_contiguous(src1), src1->name);
                //}
                //if (dst) {
                //    metal_printf("%s: dst  - %4s [%5lld, %5lld, %5lld], 1, %s\n",  __func__, ggml_type_name(dstt),  ne0,  ne1,  ne2,
                //            dst->name);
                //}

                switch (dst->op) {
                    case GGML_OP_RESHAPE:
                    case GGML_OP_VIEW:
                    case GGML_OP_TRANSPOSE:
                    case GGML_OP_PERMUTE:
                        {
                            // noop
                        } break;
                    case GGML_OP_ADD:
                        {
                            if (encoder == nil) {
                                encoder = [command_buffer computeCommandEncoder];
                            }

                            [encoder setComputePipelineState:ctx->pipeline_add];
                            [encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
                            [encoder setBuffer:id_src1 offset:offs_src1 atIndex:1];
                            [encoder setBuffer:id_dst  offset:offs_dst  atIndex:2];

                            const int64_t n = ggml_nelements(dst);

                            [encoder dispatchThreadgroups:MTLSizeMake(n, 1, 1) threadsPerThreadgroup:MTLSizeMake(1, 1, 1)];
                        } break;
                    case GGML_OP_MUL:
                        {
                            if (encoder == nil) {
                                encoder = [command_buffer computeCommandEncoder];
                            }

                            if (ggml_nelements(src1) == ne10) {
                                // src1 is a row
                                [encoder setComputePipelineState:ctx->pipeline_mul_row];
                            } else {
                                [encoder setComputePipelineState:ctx->pipeline_mul];
                            }
                            [encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
                            [encoder setBuffer:id_src1 offset:offs_src1 atIndex:1];
                            [encoder setBuffer:id_dst  offset:offs_dst  atIndex:2];
                            [encoder setBytes:&ne00 length:sizeof(ne00) atIndex:3];

                            const int64_t n = ggml_nelements(dst);

                            [encoder dispatchThreadgroups:MTLSizeMake(n, 1, 1) threadsPerThreadgroup:MTLSizeMake(1, 1, 1)];
                        } break;
                    case GGML_OP_SCALE:
                        {
                            if (encoder == nil) {
                                encoder = [command_buffer computeCommandEncoder];
                            }

                            const float scale = *(const float *) src1->data;

                            [encoder setComputePipelineState:ctx->pipeline_scale];
                            [encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
                            [encoder setBuffer:id_dst  offset:offs_dst  atIndex:1];
                            [encoder setBytes:&scale length:sizeof(scale) atIndex:2];

                            const int64_t n = ggml_nelements(dst);

                            [encoder dispatchThreadgroups:MTLSizeMake(n, 1, 1) threadsPerThreadgroup:MTLSizeMake(1, 1, 1)];
                        } break;
                    case GGML_OP_SILU:
                        {
                            if (encoder == nil) {
                                encoder = [command_buffer computeCommandEncoder];
                            }

                            [encoder setComputePipelineState:ctx->pipeline_silu];
                            [encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
                            [encoder setBuffer:id_dst  offset:offs_dst  atIndex:1];

                            const int64_t n = ggml_nelements(dst);

                            [encoder dispatchThreadgroups:MTLSizeMake(n, 1, 1) threadsPerThreadgroup:MTLSizeMake(1, 1, 1)];
                        } break;
                    case GGML_OP_RELU:
                        {
                            if (encoder == nil) {
                                encoder = [command_buffer computeCommandEncoder];
                            }

                            [encoder setComputePipelineState:ctx->pipeline_relu];
                            [encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
                            [encoder setBuffer:id_dst  offset:offs_dst  atIndex:1];

                            const int64_t n = ggml_nelements(dst);

                            [encoder dispatchThreadgroups:MTLSizeMake(n, 1, 1) threadsPerThreadgroup:MTLSizeMake(1, 1, 1)];
                        } break;
                    case GGML_OP_GELU:
                    {
                            if (encoder == nil) {
                                encoder = [command_buffer computeCommandEncoder];
                            }

                            [encoder setComputePipelineState:ctx->pipeline_gelu];
                            [encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
                            [encoder setBuffer:id_dst  offset:offs_dst  atIndex:1];

                            const int64_t n = ggml_nelements(dst);

                            [encoder dispatchThreadgroups:MTLSizeMake(n, 1, 1) threadsPerThreadgroup:MTLSizeMake(1, 1, 1)];
                    } break;
                    case GGML_OP_SOFT_MAX:
                        {
                            if (encoder == nil) {
                                encoder = [command_buffer computeCommandEncoder];
                            }

                            const int nth = 32;

                            [encoder setComputePipelineState:ctx->pipeline_soft_max];
                            [encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
                            [encoder setBuffer:id_dst  offset:offs_dst  atIndex:1];
                            [encoder setBytes:&ne00 length:sizeof(ne00) atIndex:2];
                            [encoder setBytes:&ne01 length:sizeof(ne01) atIndex:3];
                            [encoder setBytes:&ne02 length:sizeof(ne02) atIndex:4];
                            [encoder setThreadgroupMemoryLength:nth*sizeof(float) atIndex:0];

                            [encoder dispatchThreadgroups:MTLSizeMake(ne01, ne02, ne03) threadsPerThreadgroup:MTLSizeMake(nth, 1, 1)];
                        } break;
                    case GGML_OP_DIAG_MASK_INF:
                        {
                            if (encoder == nil) {
                                encoder = [command_buffer computeCommandEncoder];
                            }

                            const int n_past = ((int32_t *)(src1->data))[0];

                            [encoder setComputePipelineState:ctx->pipeline_diag_mask_inf];
                            [encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
                            [encoder setBuffer:id_dst  offset:offs_dst  atIndex:1];
                            [encoder setBytes:&ne00   length:sizeof(ne00) atIndex:2];
                            [encoder setBytes:&ne01   length:sizeof(ne01) atIndex:3];
                            [encoder setBytes:&n_past length:sizeof(int)  atIndex:4];

                            [encoder dispatchThreadgroups:MTLSizeMake(ne00, ne01, ne02) threadsPerThreadgroup:MTLSizeMake(1, 1, 1)];
                        } break;
                    case GGML_OP_MUL_MAT:
                        {
                            // TODO: needs to be updated after PR: https://github.com/ggerganov/ggml/pull/224

                            GGML_ASSERT(ne00 == ne10);
                            GGML_ASSERT(ne02 == ne12);

                            if (ggml_is_contiguous(src0) &&
                                ggml_is_contiguous(src1) &&
                                (src0t == GGML_TYPE_F32 || src0t == GGML_TYPE_F16) && ne11 > 1) {

                                if (encoder != nil) {
                                    [encoder endEncoding];
                                    encoder = nil;
                                }

                                MPSDataType src0dt = src0t == GGML_TYPE_F32 ? MPSDataTypeFloat32 : MPSDataTypeFloat16;
                                MPSDataType src1dt = src1t == GGML_TYPE_F32 ? MPSDataTypeFloat32 : MPSDataTypeFloat16;

                                // for F32 x F32 we use MPS
                                MPSMatrixDescriptor * desc0 = [MPSMatrixDescriptor
                                    matrixDescriptorWithRows:ne01 columns:ne00 rowBytes:src0->nb[1] dataType:src0dt];

                                MPSMatrixDescriptor * desc1 = [MPSMatrixDescriptor
                                    matrixDescriptorWithRows:ne11 columns:ne10 rowBytes:src1->nb[1] dataType:src1dt];

                                MPSMatrixDescriptor * desc  = [MPSMatrixDescriptor
                                    matrixDescriptorWithRows:ne1 columns:ne0 rowBytes:dst->nb[1] dataType:MPSDataTypeFloat32];

                                MPSMatrixMultiplication * mul = [[MPSMatrixMultiplication alloc]
                                    initWithDevice:ctx->device transposeLeft:false transposeRight:true
                                        resultRows:ne11 resultColumns:ne01 interiorColumns:ne00 alpha:1.0 beta:0.0];

                                // we need to do ne02 multiplications
                                // TODO: is there a way to do this in parallel - currently very slow ..
                                // TODO: might be possible to offload part of the computation to ANE using Accelerate's CBLAS
                                for (int64_t i02 = 0; i02 < ne02; ++i02) {
                                    size_t offs_src0_cur = offs_src0 + i02*nb02;
                                    size_t offs_src1_cur = offs_src1 + i02*nb12;
                                    size_t offs_dst_cur  = offs_dst  + i02*nb2;

                                    MPSMatrix * mat_src0 = [[MPSMatrix alloc] initWithBuffer:id_src0 offset:offs_src0_cur descriptor:desc0];
                                    MPSMatrix * mat_src1 = [[MPSMatrix alloc] initWithBuffer:id_src1 offset:offs_src1_cur descriptor:desc1];
                                    MPSMatrix * mat_dst  = [[MPSMatrix alloc] initWithBuffer:id_dst  offset:offs_dst_cur  descriptor:desc ];

                                    [mul encodeToCommandBuffer:command_buffer leftMatrix:mat_src1 rightMatrix:mat_src0 resultMatrix:mat_dst];
                                }
                            } else {
                                if (encoder == nil) {
                                    encoder = [command_buffer computeCommandEncoder];
                                }

                                int nth0 = 32;
                                int nth1 = 1;

                                // use custom matrix x vector kernel
                                switch (src0t) {
                                    case GGML_TYPE_F16:
                                        {
                                            GGML_ASSERT(ne02 == ne12);

                                            nth0 = 64;
                                            nth1 = 1;
                                            [encoder setComputePipelineState:ctx->pipeline_mul_mat_f16_f32];
                                        } break;
                                    case GGML_TYPE_Q4_0:
                                        {
                                            GGML_ASSERT(ne02 == 1);
                                            GGML_ASSERT(ne12 == 1);

                                            nth0 = 8;
                                            nth1 = 8;
                                            [encoder setComputePipelineState:ctx->pipeline_mul_mat_q4_0_f32];
                                        } break;
                                    case GGML_TYPE_Q4_1:
                                        {
                                            GGML_ASSERT(ne02 == 1);
                                            GGML_ASSERT(ne12 == 1);

                                            nth0 = 8;
                                            nth1 = 8;
                                            [encoder setComputePipelineState:ctx->pipeline_mul_mat_q4_1_f32];
                                        } break;
                                    case GGML_TYPE_Q2_K:
                                        {
                                            GGML_ASSERT(ne02 == 1);
                                            GGML_ASSERT(ne12 == 1);

                                            nth0 = 4;
                                            nth1 = 16;
                                            [encoder setComputePipelineState:ctx->pipeline_mul_mat_q2_K_f32];
                                        } break;
                                    case GGML_TYPE_Q3_K:
                                        {
                                            GGML_ASSERT(ne02 == 1);
                                            GGML_ASSERT(ne12 == 1);

                                            nth0 = 4;
                                            nth1 = 16;
                                            [encoder setComputePipelineState:ctx->pipeline_mul_mat_q3_K_f32];
                                        } break;
                                    case GGML_TYPE_Q4_K:
                                        {
                                            GGML_ASSERT(ne02 == 1);
                                            GGML_ASSERT(ne12 == 1);

                                            nth0 = 4;
                                            nth1 = 16;
                                            [encoder setComputePipelineState:ctx->pipeline_mul_mat_q4_K_f32];
                                        } break;
                                    case GGML_TYPE_Q5_K:
                                        {
                                            GGML_ASSERT(ne02 == 1);
                                            GGML_ASSERT(ne12 == 1);

                                            nth0 = 4;
                                            nth1 = 16;
                                            [encoder setComputePipelineState:ctx->pipeline_mul_mat_q5_K_f32];
                                        } break;
                                    case GGML_TYPE_Q6_K:
                                        {
                                            GGML_ASSERT(ne02 == 1);
                                            GGML_ASSERT(ne12 == 1);

                                            nth0 = 4;
                                            nth1 = 16;
                                            [encoder setComputePipelineState:ctx->pipeline_mul_mat_q6_K_f32];
                                        } break;
                                    default:
                                        {
                                            fprintf(stderr, "Asserting on type %d\n",(int)src0t);
                                            GGML_ASSERT(false && "not implemented");
                                        }
                                };

                                [encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
                                [encoder setBuffer:id_src1 offset:offs_src1 atIndex:1];
                                [encoder setBuffer:id_dst  offset:offs_dst  atIndex:2];
                                [encoder setBytes:&ne00 length:sizeof(ne00) atIndex:3];
                                [encoder setBytes:&ne01 length:sizeof(ne01) atIndex:4];
                                [encoder setBytes:&nb00 length:sizeof(nb00) atIndex:5];
                                [encoder setBytes:&nb01 length:sizeof(nb01) atIndex:6];
                                [encoder setBytes:&nb02 length:sizeof(nb02) atIndex:7];
                                [encoder setBytes:&ne10 length:sizeof(ne10) atIndex:8];
                                [encoder setBytes:&ne11 length:sizeof(ne11) atIndex:9];
                                [encoder setBytes:&nb10 length:sizeof(nb10) atIndex:10];
                                [encoder setBytes:&nb11 length:sizeof(nb11) atIndex:11];
                                [encoder setBytes:&nb12 length:sizeof(nb12) atIndex:12];
                                [encoder setBytes:&ne0  length:sizeof(ne0)  atIndex:13];
                                [encoder setBytes:&ne1  length:sizeof(ne1)  atIndex:14];

                                if (src0t == GGML_TYPE_Q4_0 || src0t == GGML_TYPE_Q4_1) {
                                    [encoder setThreadgroupMemoryLength:nth0*nth1*sizeof(float) atIndex:0];
                                    [encoder dispatchThreadgroups:MTLSizeMake(ne01, ne11, 1) threadsPerThreadgroup:MTLSizeMake(nth0, nth1, 1)];
                                }
                                else if (src0t == GGML_TYPE_Q2_K ||
                                         src0t == GGML_TYPE_Q3_K ||
                                         src0t == GGML_TYPE_Q4_K ||
                                         src0t == GGML_TYPE_Q5_K ||
                                         src0t == GGML_TYPE_Q6_K) {
                                    [encoder setThreadgroupMemoryLength:nth0*nth1*sizeof(float) atIndex:0];
                                    [encoder dispatchThreadgroups:MTLSizeMake(ne01, 1, 1) threadsPerThreadgroup:MTLSizeMake(nth0, nth1, 1)];
                                } else {
                                    [encoder setThreadgroupMemoryLength:nth0*sizeof(float) atIndex:0];
                                    [encoder dispatchThreadgroups:MTLSizeMake(ne01, ne11, ne12) threadsPerThreadgroup:MTLSizeMake(nth0, nth1, 1)];
                                }
                            }
                        } break;
                    case GGML_OP_GET_ROWS:
                        {
                            if (encoder == nil) {
                                encoder = [command_buffer computeCommandEncoder];
                            }

                            switch (src0->type) {
                                case GGML_TYPE_F16:  [encoder setComputePipelineState:ctx->pipeline_get_rows_f16]; break;
                                case GGML_TYPE_Q4_0: [encoder setComputePipelineState:ctx->pipeline_get_rows_q4_0]; break;
                                case GGML_TYPE_Q4_1: [encoder setComputePipelineState:ctx->pipeline_get_rows_q4_1]; break;
                                case GGML_TYPE_Q2_K: [encoder setComputePipelineState:ctx->pipeline_get_rows_q2_K]; break;
                                case GGML_TYPE_Q3_K: [encoder setComputePipelineState:ctx->pipeline_get_rows_q3_K]; break;
                                case GGML_TYPE_Q4_K: [encoder setComputePipelineState:ctx->pipeline_get_rows_q4_K]; break;
                                case GGML_TYPE_Q5_K: [encoder setComputePipelineState:ctx->pipeline_get_rows_q5_K]; break;
                                case GGML_TYPE_Q6_K: [encoder setComputePipelineState:ctx->pipeline_get_rows_q6_K]; break;
                                default: GGML_ASSERT(false && "not implemented");
                            }

                            [encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
                            [encoder setBuffer:id_src1 offset:offs_src1 atIndex:1];
                            [encoder setBuffer:id_dst  offset:offs_dst  atIndex:2];
                            [encoder setBytes:&(src0->ne[0]) length:sizeof( int64_t) atIndex:3];
                            [encoder setBytes:&(src0->nb[1]) length:sizeof(uint64_t) atIndex:4];
                            [encoder setBytes:&(dst->nb[1])  length:sizeof(uint64_t) atIndex:5];

                            const int64_t n = ggml_nelements(src1);

                            [encoder dispatchThreadgroups:MTLSizeMake(n, 1, 1) threadsPerThreadgroup:MTLSizeMake(1, 1, 1)];
                        } break;
                    case GGML_OP_RMS_NORM:
                        {
                            if (encoder == nil) {
                                encoder = [command_buffer computeCommandEncoder];
                            }

                            const float eps = 1e-6f;

                            const int nth = 256;

                            [encoder setComputePipelineState:ctx->pipeline_rms_norm];
                            [encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
                            [encoder setBuffer:id_dst  offset:offs_dst  atIndex:1];
                            [encoder setBytes:&ne00 length:sizeof( int64_t) atIndex:2];
                            [encoder setBytes:&nb01 length:sizeof(uint64_t) atIndex:3];
                            [encoder setBytes:&eps  length:sizeof(   float) atIndex:4];
                            [encoder setThreadgroupMemoryLength:nth*sizeof(float) atIndex:0];

                            const int64_t nrows = ggml_nrows(src0);

                            [encoder dispatchThreadgroups:MTLSizeMake(nrows, 1, 1) threadsPerThreadgroup:MTLSizeMake(nth, 1, 1)];
                        } break;
                    case GGML_OP_NORM:
                        {
                            if (encoder == nil) {
                                encoder = [command_buffer computeCommandEncoder];
                            }

                            const float eps = 1e-5f;

                            const int nth = 256;

                            [encoder setComputePipelineState:ctx->pipeline_norm];
                            [encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
                            [encoder setBuffer:id_dst  offset:offs_dst  atIndex:1];
                            [encoder setBytes:&ne00 length:sizeof( int64_t) atIndex:2];
                            [encoder setBytes:&nb01 length:sizeof(uint64_t) atIndex:3];
                            [encoder setBytes:&eps  length:sizeof(   float) atIndex:4];
                            [encoder setThreadgroupMemoryLength:nth*sizeof(float) atIndex:0];

                            const int64_t nrows = ggml_nrows(src0);

                            [encoder dispatchThreadgroups:MTLSizeMake(nrows, 1, 1) threadsPerThreadgroup:MTLSizeMake(nth, 1, 1)];
                        } break;
                    case GGML_OP_ALIBI:
                        {
                            if (encoder == nil) {
                                encoder = [command_buffer computeCommandEncoder];
                            }

                            GGML_ASSERT((src0t == GGML_TYPE_F32));

                            const int   n_past   = ((int32_t *) src1->data)[0]; UNUSED(n_past);
                            const int   n_head   = ((int32_t *) src1->data)[1];
                            const float max_bias = ((float *)   src1->data)[2];

                            if (__builtin_popcount(n_head) != 1) {
                                GGML_ASSERT(false && "only power-of-two n_head implemented");
                            }

                            const int n_heads_log2_floor = 1 << (int) floor(log2(n_head));
                            const float m0 = powf(2.0f, -(max_bias) / n_heads_log2_floor);

                            [encoder setComputePipelineState:ctx->pipeline_alibi_f32];
                            [encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
                            [encoder setBuffer:id_dst  offset:offs_dst  atIndex:1];
                            [encoder setBytes:&ne00 length:sizeof( int64_t) atIndex:2];
                            [encoder setBytes:&ne01 length:sizeof( int64_t) atIndex:3];
                            [encoder setBytes:&ne02 length:sizeof( int64_t) atIndex:4];
                            [encoder setBytes:&ne03 length:sizeof( int64_t) atIndex:5];
                            [encoder setBytes:&nb00 length:sizeof(uint64_t) atIndex:6];
                            [encoder setBytes:&nb01 length:sizeof(uint64_t) atIndex:7];
                            [encoder setBytes:&nb02 length:sizeof(uint64_t) atIndex:8];
                            [encoder setBytes:&nb03 length:sizeof(uint64_t) atIndex:9];
                            [encoder setBytes:&ne0  length:sizeof( int64_t) atIndex:10];
                            [encoder setBytes:&ne1  length:sizeof( int64_t) atIndex:11];
                            [encoder setBytes:&ne2  length:sizeof( int64_t) atIndex:12];
                            [encoder setBytes:&ne3  length:sizeof( int64_t) atIndex:13];
                            [encoder setBytes:&nb0  length:sizeof(uint64_t) atIndex:14];
                            [encoder setBytes:&nb1  length:sizeof(uint64_t) atIndex:15];
                            [encoder setBytes:&nb2  length:sizeof(uint64_t) atIndex:16];
                            [encoder setBytes:&nb3  length:sizeof(uint64_t) atIndex:17];
                            [encoder setBytes:&m0  length:sizeof(    float) atIndex:18];
                            const int nth = 32;
                            [encoder dispatchThreadgroups:MTLSizeMake(ne01, ne02, ne03) threadsPerThreadgroup:MTLSizeMake(nth, 1, 1)];
                        } break;
                    case GGML_OP_ROPE:
                        {
                            if (encoder == nil) {
                                encoder = [command_buffer computeCommandEncoder];
                            }

                            const int n_dims = ((int32_t *) src1->data)[1];
                            const int mode   = ((int32_t *) src1->data)[2];

                            const int n_past = ((int32_t *)(src1->data))[0];

                            [encoder setComputePipelineState:ctx->pipeline_rope];
                            [encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
                            [encoder setBuffer:id_dst  offset:offs_dst  atIndex:1];
                            [encoder setBytes:&ne00   length:sizeof( int64_t) atIndex:2];
                            [encoder setBytes:&ne01   length:sizeof( int64_t) atIndex:3];
                            [encoder setBytes:&ne02   length:sizeof( int64_t) atIndex:4];
                            [encoder setBytes:&ne03   length:sizeof( int64_t) atIndex:5];
                            [encoder setBytes:&nb00   length:sizeof(uint64_t) atIndex:6];
                            [encoder setBytes:&nb01   length:sizeof(uint64_t) atIndex:7];
                            [encoder setBytes:&nb02   length:sizeof(uint64_t) atIndex:8];
                            [encoder setBytes:&nb03   length:sizeof(uint64_t) atIndex:9];
                            [encoder setBytes:&ne0    length:sizeof( int64_t) atIndex:10];
                            [encoder setBytes:&ne1    length:sizeof( int64_t) atIndex:11];
                            [encoder setBytes:&ne2    length:sizeof( int64_t) atIndex:12];
                            [encoder setBytes:&ne3    length:sizeof( int64_t) atIndex:13];
                            [encoder setBytes:&nb0    length:sizeof(uint64_t) atIndex:14];
                            [encoder setBytes:&nb1    length:sizeof(uint64_t) atIndex:15];
                            [encoder setBytes:&nb2    length:sizeof(uint64_t) atIndex:16];
                            [encoder setBytes:&nb3    length:sizeof(uint64_t) atIndex:17];
                            [encoder setBytes:&n_past length:sizeof(     int) atIndex:18];
                            [encoder setBytes:&n_dims length:sizeof(     int) atIndex:19];
                            [encoder setBytes:&mode   length:sizeof(     int) atIndex:20];

                            [encoder dispatchThreadgroups:MTLSizeMake(ne01, ne02, ne03) threadsPerThreadgroup:MTLSizeMake(1, 1, 1)];
                        } break;
                    case GGML_OP_CPY:
                        {
                            if (encoder == nil) {
                                encoder = [command_buffer computeCommandEncoder];
                            }

                            const int nth = 32;

                            switch (src0t) {
                                case GGML_TYPE_F32:
                                    {
                                        switch (dstt) {
                                            case GGML_TYPE_F16: [encoder setComputePipelineState:ctx->pipeline_cpy_f32_f16]; break;
                                            case GGML_TYPE_F32: [encoder setComputePipelineState:ctx->pipeline_cpy_f32_f32]; break;
                                            default: GGML_ASSERT(false && "not implemented");
                                        };
                                    } break;
                                case GGML_TYPE_F16:
                                    {
                                        switch (dstt) {
                                            case GGML_TYPE_F16: [encoder setComputePipelineState:ctx->pipeline_cpy_f16_f16]; break;
                                            case GGML_TYPE_F32: GGML_ASSERT(false && "cpy_f16_f32 not implemented"); break;
                                            default: GGML_ASSERT(false && "not implemented");
                                        };
                                    } break;
                                default: GGML_ASSERT(false && "not implemented");
                            }

                            [encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
                            [encoder setBuffer:id_dst  offset:offs_dst  atIndex:1];
                            [encoder setBytes:&ne00 length:sizeof( int64_t) atIndex:2];
                            [encoder setBytes:&ne01 length:sizeof( int64_t) atIndex:3];
                            [encoder setBytes:&ne02 length:sizeof( int64_t) atIndex:4];
                            [encoder setBytes:&ne03 length:sizeof( int64_t) atIndex:5];
                            [encoder setBytes:&nb00 length:sizeof(uint64_t) atIndex:6];
                            [encoder setBytes:&nb01 length:sizeof(uint64_t) atIndex:7];
                            [encoder setBytes:&nb02 length:sizeof(uint64_t) atIndex:8];
                            [encoder setBytes:&nb03 length:sizeof(uint64_t) atIndex:9];
                            [encoder setBytes:&ne0  length:sizeof( int64_t) atIndex:10];
                            [encoder setBytes:&ne1  length:sizeof( int64_t) atIndex:11];
                            [encoder setBytes:&ne2  length:sizeof( int64_t) atIndex:12];
                            [encoder setBytes:&ne3  length:sizeof( int64_t) atIndex:13];
                            [encoder setBytes:&nb0  length:sizeof(uint64_t) atIndex:14];
                            [encoder setBytes:&nb1  length:sizeof(uint64_t) atIndex:15];
                            [encoder setBytes:&nb2  length:sizeof(uint64_t) atIndex:16];
                            [encoder setBytes:&nb3  length:sizeof(uint64_t) atIndex:17];

                            [encoder dispatchThreadgroups:MTLSizeMake(ne01, ne02, ne03) threadsPerThreadgroup:MTLSizeMake(nth, 1, 1)];
                        } break;
                    default:
                        fprintf(stderr, "%s: node %3d, op = %8s not implemented\n", __func__, i, ggml_op_name(dst->op));
                        GGML_ASSERT(false);
                }
            }

            if (encoder != nil) {
                [encoder endEncoding];
                encoder = nil;
            }

            [command_buffer commit];
        });
    }

    // wait for all threads to finish
    dispatch_barrier_sync(queue, ^{});

    [command_buffers[n_cb - 1] waitUntilCompleted];

    // check status of command buffers
    // needed to detect if the device ran out-of-memory for example (#1881)
    for (int i = 0; i < n_cb; i++) {
        MTLCommandBufferStatus status = (MTLCommandBufferStatus) [command_buffers[i] status];
        if (status != MTLCommandBufferStatusCompleted) {
            fprintf(stderr, "%s: command buffer %d failed with status %lu\n", __func__, i, status);
            GGML_ASSERT(false);
        }
    }
}