inference 0.3.0

A crate for managing the machine learning inference process
Documentation
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
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
/// @@
/// @@  .. cpp:var:: message ModelRateLimiter
/// @@
/// @@     The specifications required by the rate limiter to properly
/// @@     schedule the inference requests across the different models
/// @@     and their instances.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelRateLimiter {
    /// @@  .. cpp:var:: Resource resources (repeated)
    /// @@
    /// @@     The resources required to execute the request on a model instance.
    /// @@     Resources are just names with a corresponding count. The execution
    /// @@     of the instance will be blocked until the specificied resources are
    /// @@     available. By default an instance uses no rate-limiter resources.
    /// @@
    #[prost(message, repeated, tag = "1")]
    pub resources: ::prost::alloc::vec::Vec<model_rate_limiter::Resource>,
    /// @@  .. cpp:var:: uint32 priority
    /// @@
    /// @@     The optional weighting value to be used for prioritizing across
    /// @@     instances. An instance with priority 2 will be given 1/2 the
    /// @@     number of scheduling chances as an instance_group with priority
    /// @@     1. The default priority is 1. The priority of value 0 will be
    /// @@     treated as priority 1.
    /// @@
    #[prost(uint32, tag = "2")]
    pub priority: u32,
}
/// Nested message and enum types in `ModelRateLimiter`.
pub mod model_rate_limiter {
    /// @@  .. cpp:var:: message Resource
    /// @@
    /// @@     The resource property.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct Resource {
        /// @@  .. cpp:var:: string name
        /// @@
        /// @@     The name associated with the resource.
        /// @@
        #[prost(string, tag = "1")]
        pub name: ::prost::alloc::string::String,
        /// @@  .. cpp:var:: bool global
        /// @@
        /// @@     Whether or not the resource is global. If true then the resource
        /// @@     is assumed to be shared among the devices otherwise specified
        /// @@     count of the resource is assumed for each device associated
        /// @@     with the instance.
        /// @@
        #[prost(bool, tag = "2")]
        pub global: bool,
        /// @@  .. cpp:var:: uint32 count
        /// @@
        /// @@     The number of resources required for the execution of the model
        /// @@     instance.
        /// @@
        #[prost(uint32, tag = "3")]
        pub count: u32,
    }
}
/// @@
/// @@.. cpp:var:: message ModelInstanceGroup
/// @@
/// @@   A group of one or more instances of a model and resources made
/// @@   available for those instances.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelInstanceGroup {
    /// @@  .. cpp:var:: string name
    /// @@
    /// @@     Optional name of this group of instances. If not specified the
    /// @@     name will be formed as <model name>_<group number>. The name of
    /// @@     individual instances will be further formed by a unique instance
    /// @@     number and GPU index:
    /// @@
    #[prost(string, tag = "1")]
    pub name: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: Kind kind
    /// @@
    /// @@     The kind of this instance group. Default is KIND_AUTO. If
    /// @@     KIND_AUTO or KIND_GPU then both 'count' and 'gpu' are valid and
    /// @@     may be specified. If KIND_CPU or KIND_MODEL only 'count' is valid
    /// @@     and 'gpu' cannot be specified.
    /// @@
    #[prost(enumeration = "model_instance_group::Kind", tag = "4")]
    pub kind: i32,
    /// @@  .. cpp:var:: int32 count
    /// @@
    /// @@     For a group assigned to GPU, the number of instances created for
    /// @@     each GPU listed in 'gpus'. For a group assigned to CPU the number
    /// @@     of instances created. Default is 1.
    #[prost(int32, tag = "2")]
    pub count: i32,
    /// @@  .. cpp:var:: ModelRateLimiter rate_limiter
    /// @@
    /// @@     The rate limiter specific settings to be associated with this
    /// @@     instance group. Optional, if not specified no rate limiting
    /// @@     will be applied to this instance group.
    /// @@
    #[prost(message, optional, tag = "6")]
    pub rate_limiter: ::core::option::Option<ModelRateLimiter>,
    /// @@  .. cpp:var:: int32 gpus (repeated)
    /// @@
    /// @@     GPU(s) where instances should be available. For each GPU listed,
    /// @@     'count' instances of the model will be available. Setting 'gpus'
    /// @@     to empty (or not specifying at all) is eqivalent to listing all
    /// @@     available GPUs.
    /// @@
    #[prost(int32, repeated, tag = "3")]
    pub gpus: ::prost::alloc::vec::Vec<i32>,
    /// @@  .. cpp:var:: SecondaryDevice secondary_devices (repeated)
    /// @@
    /// @@     Secondary devices that are required by instances specified by this
    /// @@     instance group. Optional.
    /// @@
    #[prost(message, repeated, tag = "8")]
    pub secondary_devices: ::prost::alloc::vec::Vec<
        model_instance_group::SecondaryDevice,
    >,
    /// @@  .. cpp:var:: string profile (repeated)
    /// @@
    /// @@     For TensorRT models containing multiple optimization profile, this
    /// @@     parameter specifies a set of optimization profiles available to this
    /// @@     instance group. The inference server will choose the optimal profile
    /// @@     based on the shapes of the input tensors. This field should lie
    /// @@     between 0 and <TotalNumberOfOptimizationProfilesInPlanModel> - 1
    /// @@     and be specified only for TensorRT backend, otherwise an error will
    /// @@     be generated. If not specified, the server will select the first
    /// @@     optimization profile by default.
    /// @@
    #[prost(string, repeated, tag = "5")]
    pub profile: ::prost::alloc::vec::Vec<::prost::alloc::string::String>,
    /// @@  .. cpp:var:: bool passive
    /// @@
    /// @@     Whether the instances within this instance group will be accepting
    /// @@     inference requests from the scheduler. If true, the instances will
    /// @@     not be added to the scheduler. Default value is false.
    /// @@
    #[prost(bool, tag = "7")]
    pub passive: bool,
    /// @@  .. cpp:var:: string host_policy
    /// @@
    /// @@     The host policy name that the instance to be associated with.
    /// @@     The default value is set to reflect the device kind of the instance,
    /// @@     for instance, KIND_CPU is "cpu", KIND_MODEL is "model" and
    /// @@     KIND_GPU is "gpu_<gpu_id>".
    /// @@
    #[prost(string, tag = "9")]
    pub host_policy: ::prost::alloc::string::String,
}
/// Nested message and enum types in `ModelInstanceGroup`.
pub mod model_instance_group {
    /// @@
    /// @@  .. cpp:var:: message SecondaryDevice
    /// @@
    /// @@     A secondary device required for a model instance.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct SecondaryDevice {
        /// @@  .. cpp:var:: SecondaryDeviceKind kind
        /// @@
        /// @@     The secondary device kind.
        /// @@
        #[prost(enumeration = "secondary_device::SecondaryDeviceKind", tag = "1")]
        pub kind: i32,
        /// @@  .. cpp:var:: int64 device_id
        /// @@
        /// @@     Identifier for the secondary device.
        /// @@
        #[prost(int64, tag = "2")]
        pub device_id: i64,
    }
    /// Nested message and enum types in `SecondaryDevice`.
    pub mod secondary_device {
        /// @@
        /// @@  .. cpp:enum:: SecondaryDeviceKind
        /// @@
        /// @@     The kind of the secondary device.
        /// @@
        #[derive(
            Clone,
            Copy,
            Debug,
            PartialEq,
            Eq,
            Hash,
            PartialOrd,
            Ord,
            ::prost::Enumeration
        )]
        #[repr(i32)]
        pub enum SecondaryDeviceKind {
            /// @@    .. cpp:enumerator:: SecondaryDeviceKind::KIND_NVDLA = 0
            /// @@
            /// @@       An NVDLA core. <http://nvdla.org>
            /// @@       Currently KIND_NVDLA is only supported by the TensorRT backend.
            /// @@
            KindNvdla = 0,
        }
        impl SecondaryDeviceKind {
            /// String value of the enum field names used in the ProtoBuf definition.
            ///
            /// The values are not transformed in any way and thus are considered stable
            /// (if the ProtoBuf definition does not change) and safe for programmatic use.
            pub fn as_str_name(&self) -> &'static str {
                match self {
                    SecondaryDeviceKind::KindNvdla => "KIND_NVDLA",
                }
            }
            /// Creates an enum from field names used in the ProtoBuf definition.
            pub fn from_str_name(value: &str) -> ::core::option::Option<Self> {
                match value {
                    "KIND_NVDLA" => Some(Self::KindNvdla),
                    _ => None,
                }
            }
        }
    }
    /// @@
    /// @@  .. cpp:enum:: Kind
    /// @@
    /// @@     Kind of this instance group.
    /// @@
    #[derive(
        Clone,
        Copy,
        Debug,
        PartialEq,
        Eq,
        Hash,
        PartialOrd,
        Ord,
        ::prost::Enumeration
    )]
    #[repr(i32)]
    pub enum Kind {
        /// @@    .. cpp:enumerator:: Kind::KIND_AUTO = 0
        /// @@
        /// @@       This instance group represents instances that can run on either
        /// @@       CPU or GPU. If all GPUs listed in 'gpus' are available then
        /// @@       instances will be created on GPU(s), otherwise instances will
        /// @@       be created on CPU.
        /// @@
        Auto = 0,
        /// @@    .. cpp:enumerator:: Kind::KIND_GPU = 1
        /// @@
        /// @@       This instance group represents instances that must run on the
        /// @@       GPU.
        /// @@
        Gpu = 1,
        /// @@    .. cpp:enumerator:: Kind::KIND_CPU = 2
        /// @@
        /// @@       This instance group represents instances that must run on the
        /// @@       CPU.
        /// @@
        Cpu = 2,
        /// @@    .. cpp:enumerator:: Kind::KIND_MODEL = 3
        /// @@
        /// @@       This instance group represents instances that should run on the
        /// @@       CPU and/or GPU(s) as specified by the model or backend itself.
        /// @@       The inference server will not override the model/backend
        /// @@       settings.
        /// @@
        Model = 3,
    }
    impl Kind {
        /// String value of the enum field names used in the ProtoBuf definition.
        ///
        /// The values are not transformed in any way and thus are considered stable
        /// (if the ProtoBuf definition does not change) and safe for programmatic use.
        pub fn as_str_name(&self) -> &'static str {
            match self {
                Kind::Auto => "KIND_AUTO",
                Kind::Gpu => "KIND_GPU",
                Kind::Cpu => "KIND_CPU",
                Kind::Model => "KIND_MODEL",
            }
        }
        /// Creates an enum from field names used in the ProtoBuf definition.
        pub fn from_str_name(value: &str) -> ::core::option::Option<Self> {
            match value {
                "KIND_AUTO" => Some(Self::Auto),
                "KIND_GPU" => Some(Self::Gpu),
                "KIND_CPU" => Some(Self::Cpu),
                "KIND_MODEL" => Some(Self::Model),
                _ => None,
            }
        }
    }
}
/// @@
/// @@.. cpp:var:: message ModelTensorReshape
/// @@
/// @@   Reshape specification for input and output tensors.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelTensorReshape {
    /// @@  .. cpp:var:: int64 shape (repeated)
    /// @@
    /// @@     The shape to use for reshaping.
    /// @@
    #[prost(int64, repeated, tag = "1")]
    pub shape: ::prost::alloc::vec::Vec<i64>,
}
/// @@
/// @@.. cpp:var:: message ModelInput
/// @@
/// @@   An input required by the model.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelInput {
    /// @@  .. cpp:var:: string name
    /// @@
    /// @@     The name of the input.
    /// @@
    #[prost(string, tag = "1")]
    pub name: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: DataType data_type
    /// @@
    /// @@     The data-type of the input.
    /// @@
    #[prost(enumeration = "DataType", tag = "2")]
    pub data_type: i32,
    /// @@  .. cpp:var:: Format format
    /// @@
    /// @@     The format of the input. Optional.
    /// @@
    #[prost(enumeration = "model_input::Format", tag = "3")]
    pub format: i32,
    /// @@  .. cpp:var:: int64 dims (repeated)
    /// @@
    /// @@     The dimensions/shape of the input tensor that must be provided
    /// @@     when invoking the inference API for this model.
    /// @@
    #[prost(int64, repeated, tag = "4")]
    pub dims: ::prost::alloc::vec::Vec<i64>,
    /// @@  .. cpp:var:: ModelTensorReshape reshape
    /// @@
    /// @@     The shape expected for this input by the backend. The input will
    /// @@     be reshaped to this before being presented to the backend. The
    /// @@     reshape must have the same number of elements as the input shape
    /// @@     specified by 'dims'. Optional.
    /// @@
    #[prost(message, optional, tag = "5")]
    pub reshape: ::core::option::Option<ModelTensorReshape>,
    /// @@  .. cpp:var:: bool is_shape_tensor
    /// @@
    /// @@     Whether or not the input is a shape tensor to the model. This field
    /// @@     is currently supported only for the TensorRT model. An error will be
    /// @@     generated if this specification does not comply with underlying
    /// @@     model.
    /// @@
    #[prost(bool, tag = "6")]
    pub is_shape_tensor: bool,
    /// @@  .. cpp:var:: bool allow_ragged_batch
    /// @@
    /// @@     Whether or not the input is allowed to be "ragged" in a dynamically
    /// @@     created batch. Default is false indicating that two requests will
    /// @@     only be batched if this tensor has the same shape in both requests.
    /// @@     True indicates that two requests can be batched even if this tensor
    /// @@     has a different shape in each request.
    /// @@
    #[prost(bool, tag = "7")]
    pub allow_ragged_batch: bool,
    /// @@  .. cpp:var:: bool optional
    /// @@
    /// @@     Whether or not the input is optional for the model execution.
    /// @@     If true, the input is not required in the inference request.
    /// @@     Default value is false.
    /// @@
    #[prost(bool, tag = "8")]
    pub optional: bool,
}
/// Nested message and enum types in `ModelInput`.
pub mod model_input {
    /// @@
    /// @@  .. cpp:enum:: Format
    /// @@
    /// @@     The format for the input.
    /// @@
    #[derive(
        Clone,
        Copy,
        Debug,
        PartialEq,
        Eq,
        Hash,
        PartialOrd,
        Ord,
        ::prost::Enumeration
    )]
    #[repr(i32)]
    pub enum Format {
        /// @@    .. cpp:enumerator:: Format::FORMAT_NONE = 0
        /// @@
        /// @@       The input has no specific format. This is the default.
        /// @@
        None = 0,
        /// @@    .. cpp:enumerator:: Format::FORMAT_NHWC = 1
        /// @@
        /// @@       HWC image format. Tensors with this format require 3 dimensions
        /// @@       if the model does not support batching (max_batch_size = 0) or 4
        /// @@       dimensions if the model does support batching (max_batch_size
        /// @@       >= 1). In either case the 'dims' below should only specify the
        /// @@       3 non-batch dimensions (i.e. HWC or CHW).
        /// @@
        Nhwc = 1,
        /// @@    .. cpp:enumerator:: Format::FORMAT_NCHW = 2
        /// @@
        /// @@       CHW image format. Tensors with this format require 3 dimensions
        /// @@       if the model does not support batching (max_batch_size = 0) or 4
        /// @@       dimensions if the model does support batching (max_batch_size
        /// @@       >= 1). In either case the 'dims' below should only specify the
        /// @@       3 non-batch dimensions (i.e. HWC or CHW).
        /// @@
        Nchw = 2,
    }
    impl Format {
        /// String value of the enum field names used in the ProtoBuf definition.
        ///
        /// The values are not transformed in any way and thus are considered stable
        /// (if the ProtoBuf definition does not change) and safe for programmatic use.
        pub fn as_str_name(&self) -> &'static str {
            match self {
                Format::None => "FORMAT_NONE",
                Format::Nhwc => "FORMAT_NHWC",
                Format::Nchw => "FORMAT_NCHW",
            }
        }
        /// Creates an enum from field names used in the ProtoBuf definition.
        pub fn from_str_name(value: &str) -> ::core::option::Option<Self> {
            match value {
                "FORMAT_NONE" => Some(Self::None),
                "FORMAT_NHWC" => Some(Self::Nhwc),
                "FORMAT_NCHW" => Some(Self::Nchw),
                _ => None,
            }
        }
    }
}
/// @@
/// @@.. cpp:var:: message ModelOutput
/// @@
/// @@   An output produced by the model.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelOutput {
    /// @@  .. cpp:var:: string name
    /// @@
    /// @@     The name of the output.
    /// @@
    #[prost(string, tag = "1")]
    pub name: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: DataType data_type
    /// @@
    /// @@     The data-type of the output.
    /// @@
    #[prost(enumeration = "DataType", tag = "2")]
    pub data_type: i32,
    /// @@  .. cpp:var:: int64 dims (repeated)
    /// @@
    /// @@     The dimensions/shape of the output tensor.
    /// @@
    #[prost(int64, repeated, tag = "3")]
    pub dims: ::prost::alloc::vec::Vec<i64>,
    /// @@  .. cpp:var:: ModelTensorReshape reshape
    /// @@
    /// @@     The shape produced for this output by the backend. The output will
    /// @@     be reshaped from this to the shape specifed in 'dims' before being
    /// @@     returned in the inference response. The reshape must have the same
    /// @@     number of elements as the output shape specified by 'dims'. Optional.
    /// @@
    #[prost(message, optional, tag = "5")]
    pub reshape: ::core::option::Option<ModelTensorReshape>,
    /// @@  .. cpp:var:: string label_filename
    /// @@
    /// @@     The label file associated with this output. Should be specified only
    /// @@     for outputs that represent classifications. Optional.
    /// @@
    #[prost(string, tag = "4")]
    pub label_filename: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: bool is_shape_tensor
    /// @@
    /// @@     Whether or not the output is a shape tensor to the model. This field
    /// @@     is currently supported only for the TensorRT model. An error will be
    /// @@     generated if this specification does not comply with underlying
    /// @@     model.
    /// @@
    #[prost(bool, tag = "6")]
    pub is_shape_tensor: bool,
}
/// @@  .. cpp:var:: message BatchInput
/// @@
/// @@     A batch input is an additional input that must be added by
/// @@     the backend based on all the requests in a batch.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct BatchInput {
    /// @@    .. cpp:var:: Kind kind
    /// @@
    /// @@       The kind of this batch input.
    /// @@
    #[prost(enumeration = "batch_input::Kind", tag = "1")]
    pub kind: i32,
    /// @@    .. cpp:var:: string target_name (repeated)
    /// @@
    /// @@       The name of the model inputs that the backend will create
    /// @@       for this batch input.
    /// @@
    #[prost(string, repeated, tag = "2")]
    pub target_name: ::prost::alloc::vec::Vec<::prost::alloc::string::String>,
    /// @@    .. cpp:var:: DataType data_type
    /// @@
    /// @@       The input's datatype. The data type can be TYPE_INT32 or
    /// @@       TYPE_FP32.
    /// @@
    #[prost(enumeration = "DataType", tag = "3")]
    pub data_type: i32,
    /// @@    .. cpp:var:: string source_input (repeated)
    /// @@
    /// @@       The backend derives the value for each batch input from one or
    /// @@       more other inputs. 'source_input' gives the names of those
    /// @@       inputs.
    /// @@
    #[prost(string, repeated, tag = "4")]
    pub source_input: ::prost::alloc::vec::Vec<::prost::alloc::string::String>,
}
/// Nested message and enum types in `BatchInput`.
pub mod batch_input {
    /// @@
    /// @@    .. cpp:enum:: Kind
    /// @@
    /// @@       The kind of the batch input.
    /// @@
    #[derive(
        Clone,
        Copy,
        Debug,
        PartialEq,
        Eq,
        Hash,
        PartialOrd,
        Ord,
        ::prost::Enumeration
    )]
    #[repr(i32)]
    pub enum Kind {
        /// @@      .. cpp:enumerator:: Kind::BATCH_ELEMENT_COUNT = 0
        /// @@
        /// @@         The element count of the 'source_input' will be added as
        /// @@         input with shape \[1\].
        /// @@
        BatchElementCount = 0,
        /// @@      .. cpp:enumerator:: Kind::BATCH_ACCUMULATED_ELEMENT_COUNT = 1
        /// @@
        /// @@         The accumulated element count of the 'source_input' will be
        /// @@         added as input with shape \[1\]. For example, if there is a
        /// @@         batch of two request, each with 2 elements, an input of value
        /// @@         2 will be added to the first request, and an input of value
        /// @@         4 will be added to the second request.
        /// @@
        BatchAccumulatedElementCount = 1,
        /// @@      .. cpp:enumerator::
        /// @@         Kind::BATCH_ACCUMULATED_ELEMENT_COUNT_WITH_ZERO = 2
        /// @@
        /// @@         The accumulated element count of the 'source_input' will be
        /// @@         added as input with shape \[1\], except for the first request
        /// @@         in the batch. For the first request in the batch, the input
        /// @@         will have shape \[2\] where the first element is value 0.
        /// @@
        BatchAccumulatedElementCountWithZero = 2,
        /// @@      .. cpp:enumerator:: Kind::BATCH_MAX_ELEMENT_COUNT_AS_SHAPE = 3
        /// @@
        /// @@         Among the requests in the batch, the max element count of the
        /// @@         'source_input' will be added as input with shape
        /// @@         \[max_element_count\] for the first request in the batch.
        /// @@         For other requests, such input will be with shape \[0\].
        /// @@         The data of the tensor will be uninitialized.
        /// @@
        BatchMaxElementCountAsShape = 3,
        /// @@      .. cpp:enumerator:: Kind::BATCH_ITEM_SHAPE = 4
        /// @@
        /// @@         Among the requests in the batch, the shape of the
        /// @@         'source_input' will be added as input with shape
        /// @@         [batch_size, len(input_dim)]. For example, if one
        /// @@         batch-2 input with shape [3, 1] and batch-1 input
        /// @@         with shape [2, 2] are batched, the batch input will
        /// @@         have shape [3, 2] and value [ [3, 1], [3, 1], [2, 2]].
        /// @@
        BatchItemShape = 4,
        /// @@      .. cpp:enumerator:: Kind::BATCH_ITEM_SHAPE_FLATTEN = 5
        /// @@
        /// @@         Among the requests in the batch, the shape of the
        /// @@         'source_input' will be added as input with single dimensional
        /// @@         shape [batch_size * len(input_dim)]. For example, if one
        /// @@         batch-2 input with shape [3, 1] and batch-1 input
        /// @@         with shape [2, 2] are batched, the batch input will
        /// @@         have shape \[6\] and value [3, 1, 3, 1, 2, 2].
        /// @@
        BatchItemShapeFlatten = 5,
    }
    impl Kind {
        /// String value of the enum field names used in the ProtoBuf definition.
        ///
        /// The values are not transformed in any way and thus are considered stable
        /// (if the ProtoBuf definition does not change) and safe for programmatic use.
        pub fn as_str_name(&self) -> &'static str {
            match self {
                Kind::BatchElementCount => "BATCH_ELEMENT_COUNT",
                Kind::BatchAccumulatedElementCount => "BATCH_ACCUMULATED_ELEMENT_COUNT",
                Kind::BatchAccumulatedElementCountWithZero => {
                    "BATCH_ACCUMULATED_ELEMENT_COUNT_WITH_ZERO"
                }
                Kind::BatchMaxElementCountAsShape => "BATCH_MAX_ELEMENT_COUNT_AS_SHAPE",
                Kind::BatchItemShape => "BATCH_ITEM_SHAPE",
                Kind::BatchItemShapeFlatten => "BATCH_ITEM_SHAPE_FLATTEN",
            }
        }
        /// Creates an enum from field names used in the ProtoBuf definition.
        pub fn from_str_name(value: &str) -> ::core::option::Option<Self> {
            match value {
                "BATCH_ELEMENT_COUNT" => Some(Self::BatchElementCount),
                "BATCH_ACCUMULATED_ELEMENT_COUNT" => {
                    Some(Self::BatchAccumulatedElementCount)
                }
                "BATCH_ACCUMULATED_ELEMENT_COUNT_WITH_ZERO" => {
                    Some(Self::BatchAccumulatedElementCountWithZero)
                }
                "BATCH_MAX_ELEMENT_COUNT_AS_SHAPE" => {
                    Some(Self::BatchMaxElementCountAsShape)
                }
                "BATCH_ITEM_SHAPE" => Some(Self::BatchItemShape),
                "BATCH_ITEM_SHAPE_FLATTEN" => Some(Self::BatchItemShapeFlatten),
                _ => None,
            }
        }
    }
}
/// @@.. cpp:var:: message BatchOutput
/// @@
/// @@   A batch output is an output produced by the model that must be handled
/// @@   differently by the backend based on all the requests in a batch.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct BatchOutput {
    /// @@  .. cpp:var:: string target_name (repeated)
    /// @@
    /// @@     The name of the outputs to be produced by this batch output
    /// @@     specification.
    /// @@
    #[prost(string, repeated, tag = "1")]
    pub target_name: ::prost::alloc::vec::Vec<::prost::alloc::string::String>,
    /// @@  .. cpp:var:: Kind kind
    /// @@
    /// @@     The kind of this batch output.
    /// @@
    #[prost(enumeration = "batch_output::Kind", tag = "2")]
    pub kind: i32,
    /// @@  .. cpp:var:: string source_input (repeated)
    /// @@
    /// @@     The backend derives each batch output from one or more inputs.
    /// @@     'source_input' gives the names of those inputs.
    /// @@
    #[prost(string, repeated, tag = "3")]
    pub source_input: ::prost::alloc::vec::Vec<::prost::alloc::string::String>,
}
/// Nested message and enum types in `BatchOutput`.
pub mod batch_output {
    /// @@
    /// @@  .. cpp:enum:: Kind
    /// @@
    /// @@     The kind of the batch output.
    /// @@
    #[derive(
        Clone,
        Copy,
        Debug,
        PartialEq,
        Eq,
        Hash,
        PartialOrd,
        Ord,
        ::prost::Enumeration
    )]
    #[repr(i32)]
    pub enum Kind {
        /// @@    .. cpp:enumerator:: Kind::BATCH_SCATTER_WITH_INPUT_SHAPE = 0
        /// @@
        /// @@       The output should be scattered according to the shape of
        /// @@       'source_input'. The dynamic dimension of the output will
        /// @@       be set to the value of the same dimension in the input.
        /// @@
        BatchScatterWithInputShape = 0,
    }
    impl Kind {
        /// String value of the enum field names used in the ProtoBuf definition.
        ///
        /// The values are not transformed in any way and thus are considered stable
        /// (if the ProtoBuf definition does not change) and safe for programmatic use.
        pub fn as_str_name(&self) -> &'static str {
            match self {
                Kind::BatchScatterWithInputShape => "BATCH_SCATTER_WITH_INPUT_SHAPE",
            }
        }
        /// Creates an enum from field names used in the ProtoBuf definition.
        pub fn from_str_name(value: &str) -> ::core::option::Option<Self> {
            match value {
                "BATCH_SCATTER_WITH_INPUT_SHAPE" => {
                    Some(Self::BatchScatterWithInputShape)
                }
                _ => None,
            }
        }
    }
}
/// @@
/// @@.. cpp:var:: message ModelVersionPolicy
/// @@
/// @@   Policy indicating which versions of a model should be made
/// @@   available by the inference server.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelVersionPolicy {
    /// @@  .. cpp:var:: oneof policy_choice
    /// @@
    /// @@     Each model must implement only a single version policy. The
    /// @@     default policy is 'Latest'.
    /// @@
    #[prost(oneof = "model_version_policy::PolicyChoice", tags = "1, 2, 3")]
    pub policy_choice: ::core::option::Option<model_version_policy::PolicyChoice>,
}
/// Nested message and enum types in `ModelVersionPolicy`.
pub mod model_version_policy {
    /// @@  .. cpp:var:: message Latest
    /// @@
    /// @@     Serve only the latest version(s) of a model. This is
    /// @@     the default policy.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct Latest {
        /// @@    .. cpp:var:: uint32 num_versions
        /// @@
        /// @@       Serve only the 'num_versions' highest-numbered versions. T
        /// @@       The default value of 'num_versions' is 1, indicating that by
        /// @@       default only the single highest-number version of a
        /// @@       model will be served.
        /// @@
        #[prost(uint32, tag = "1")]
        pub num_versions: u32,
    }
    /// @@  .. cpp:var:: message All
    /// @@
    /// @@     Serve all versions of the model.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct All {}
    /// @@  .. cpp:var:: message Specific
    /// @@
    /// @@     Serve only specific versions of the model.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct Specific {
        /// @@    .. cpp:var:: int64 versions (repeated)
        /// @@
        /// @@       The specific versions of the model that will be served.
        /// @@
        #[prost(int64, repeated, tag = "1")]
        pub versions: ::prost::alloc::vec::Vec<i64>,
    }
    /// @@  .. cpp:var:: oneof policy_choice
    /// @@
    /// @@     Each model must implement only a single version policy. The
    /// @@     default policy is 'Latest'.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Oneof)]
    pub enum PolicyChoice {
        /// @@    .. cpp:var:: Latest latest
        /// @@
        /// @@       Serve only latest version(s) of the model.
        /// @@
        #[prost(message, tag = "1")]
        Latest(Latest),
        /// @@    .. cpp:var:: All all
        /// @@
        /// @@       Serve all versions of the model.
        /// @@
        #[prost(message, tag = "2")]
        All(All),
        /// @@    .. cpp:var:: Specific specific
        /// @@
        /// @@       Serve only specific version(s) of the model.
        /// @@
        #[prost(message, tag = "3")]
        Specific(Specific),
    }
}
/// @@
/// @@.. cpp:var:: message ModelOptimizationPolicy
/// @@
/// @@   Optimization settings for a model. These settings control if/how a
/// @@   model is optimized and prioritized by the backend framework when
/// @@   it is loaded.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelOptimizationPolicy {
    /// @@  .. cpp:var:: Graph graph
    /// @@
    /// @@     The graph optimization setting for the model. Optional.
    /// @@
    #[prost(message, optional, tag = "1")]
    pub graph: ::core::option::Option<model_optimization_policy::Graph>,
    /// @@  .. cpp:var:: ModelPriority priority
    /// @@
    /// @@     The priority setting for the model. Optional.
    /// @@
    #[prost(enumeration = "model_optimization_policy::ModelPriority", tag = "2")]
    pub priority: i32,
    /// @@  .. cpp:var:: Cuda cuda
    /// @@
    /// @@     CUDA-specific optimization settings. Optional.
    /// @@
    #[prost(message, optional, tag = "3")]
    pub cuda: ::core::option::Option<model_optimization_policy::Cuda>,
    /// @@  .. cpp:var:: ExecutionAccelerators execution_accelerators
    /// @@
    /// @@     The accelerators used for the model. Optional.
    /// @@
    #[prost(message, optional, tag = "4")]
    pub execution_accelerators: ::core::option::Option<
        model_optimization_policy::ExecutionAccelerators,
    >,
    /// @@  .. cpp:var:: PinnedMemoryBuffer input_pinned_memory
    /// @@
    /// @@     Use pinned memory buffer when the data transfer for inputs
    /// @@     is between GPU memory and non-pinned system memory.
    /// @@     Default is true.
    /// @@
    #[prost(message, optional, tag = "5")]
    pub input_pinned_memory: ::core::option::Option<
        model_optimization_policy::PinnedMemoryBuffer,
    >,
    /// @@  .. cpp:var:: PinnedMemoryBuffer output_pinned_memory
    /// @@
    /// @@     Use pinned memory buffer when the data transfer for outputs
    /// @@     is between GPU memory and non-pinned system memory.
    /// @@     Default is true.
    /// @@
    #[prost(message, optional, tag = "6")]
    pub output_pinned_memory: ::core::option::Option<
        model_optimization_policy::PinnedMemoryBuffer,
    >,
    /// @@  .. cpp:var:: uint32 gather_kernel_buffer_threshold
    /// @@
    /// @@     The backend may use a gather kernel to gather input data if the
    /// @@     device has direct access to the source buffer and the destination
    /// @@     buffer. In such case, the gather kernel will be used only if the
    /// @@     number of buffers to be gathered is greater or equal to
    /// @@     the specifed value. If 0, the gather kernel will be disabled.
    /// @@     Default value is 0.
    /// @@     Currently only recognized by TensorRT backend.
    /// @@
    #[prost(uint32, tag = "7")]
    pub gather_kernel_buffer_threshold: u32,
    /// @@  .. cpp:var:: bool eager_batching
    /// @@
    /// @@     Start preparing the next batch before the model instance is ready
    /// @@     for the next inference. This option can be used to overlap the
    /// @@     batch preparation with model execution, with the trade-off that
    /// @@     the next batch might be smaller than what it could have been.
    /// @@     Default value is false.
    /// @@     Currently only recognized by TensorRT backend.
    /// @@
    #[prost(bool, tag = "8")]
    pub eager_batching: bool,
}
/// Nested message and enum types in `ModelOptimizationPolicy`.
pub mod model_optimization_policy {
    /// @@
    /// @@  .. cpp:var:: message Graph
    /// @@
    /// @@     Enable generic graph optimization of the model. If not specified
    /// @@     the framework's default level of optimization is used. Supports
    /// @@     TensorFlow graphdef and savedmodel and Onnx models. For TensorFlow
    /// @@     causes XLA to be enabled/disabled for the model. For Onnx defaults
    /// @@     to enabling all optimizations, -1 enables only basic optimizations,
    /// @@     +1 enables only basic and extended optimizations.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct Graph {
        /// @@    .. cpp:var:: int32 level
        /// @@
        /// @@       The optimization level. Defaults to 0 (zero) if not specified.
        /// @@
        /// @@         - -1: Disabled
        /// @@         -  0: Framework default
        /// @@         -  1+: Enable optimization level (greater values indicate
        /// @@            higher optimization levels)
        /// @@
        #[prost(int32, tag = "1")]
        pub level: i32,
    }
    /// @@
    /// @@  .. cpp:var:: message Cuda
    /// @@
    /// @@     CUDA-specific optimization settings.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct Cuda {
        /// @@    .. cpp:var:: bool graphs
        /// @@
        /// @@       Use CUDA graphs API to capture model operations and execute
        /// @@       them more efficiently. Default value is false.
        /// @@       Currently only recognized by TensorRT backend.
        /// @@
        #[prost(bool, tag = "1")]
        pub graphs: bool,
        /// @@    .. cpp:var:: bool busy_wait_events
        /// @@
        /// @@       Use busy-waiting to synchronize CUDA events to achieve minimum
        /// @@       latency from event complete to host thread to be notified, with
        /// @@       the cost of high CPU load. Default value is false.
        /// @@       Currently only recognized by TensorRT backend.
        /// @@
        #[prost(bool, tag = "2")]
        pub busy_wait_events: bool,
        /// @@    .. cpp:var:: GraphSpec graph_spec (repeated)
        /// @@
        /// @@       Specification of the CUDA graph to be captured. If not specified
        /// @@       and 'graphs' is true, the default CUDA graphs will be captured
        /// @@       based on model settings.
        /// @@       Currently only recognized by TensorRT backend.
        /// @@
        #[prost(message, repeated, tag = "3")]
        pub graph_spec: ::prost::alloc::vec::Vec<cuda::GraphSpec>,
        /// @@    .. cpp:var:: bool output_copy_stream
        /// @@
        /// @@       Uses a CUDA stream separate from the inference stream to copy the
        /// @@       output to host. However, be aware that setting this option to
        /// @@       true will lead to an increase in the memory consumption of the
        /// @@       model as Triton will allocate twice as much GPU memory for its
        /// @@       I/O tensor buffers. Default value is false.
        /// @@       Currently only recognized by TensorRT backend.
        /// @@
        #[prost(bool, tag = "4")]
        pub output_copy_stream: bool,
    }
    /// Nested message and enum types in `Cuda`.
    pub mod cuda {
        /// @@    .. cpp:var:: message GraphSpec
        /// @@
        /// @@       Specification of the CUDA graph to be captured.
        /// @@
        #[allow(clippy::derive_partial_eq_without_eq)]
        #[derive(Clone, PartialEq, ::prost::Message)]
        pub struct GraphSpec {
            /// @@      .. cpp:var:: int32 batch_size
            /// @@
            /// @@         The batch size of the CUDA graph. If 'max_batch_size' is 0,
            /// @@         'batch_size' must be set to 0. Otherwise, 'batch_size' must
            /// @@         be set to value between 1 and 'max_batch_size'.
            /// @@
            #[prost(int32, tag = "1")]
            pub batch_size: i32,
            /// @@      .. cpp:var:: map<string, Shape> input
            /// @@
            /// @@         The specification of the inputs. 'Shape' is the shape of the
            /// @@         input without batching dimension.
            /// @@
            #[prost(map = "string, message", tag = "2")]
            pub input: ::std::collections::HashMap<
                ::prost::alloc::string::String,
                graph_spec::Shape,
            >,
            /// @@      .. cpp:var:: LowerBound graph_lower_bound
            /// @@
            /// @@         Specify the lower bound of the CUDA graph. Optional.
            /// @@         If specified, the graph can be used for input shapes and
            /// @@         batch sizes that are in closed interval between the lower
            /// @@         bound specification and graph specification. For dynamic
            /// @@         shape model, this allows CUDA graphs to be launched
            /// @@         frequently without capturing all possible shape combinations.
            /// @@         However, using graph for shape combinations different from
            /// @@         the one used for capturing introduces uninitialized data for
            /// @@         execution and it may distort the inference result if
            /// @@         the model is sensitive to uninitialized data.
            /// @@
            #[prost(message, optional, tag = "3")]
            pub graph_lower_bound: ::core::option::Option<graph_spec::LowerBound>,
        }
        /// Nested message and enum types in `GraphSpec`.
        pub mod graph_spec {
            /// @@      .. cpp:var:: message Dims
            /// @@
            /// @@         Specification of tensor dimension.
            /// @@
            #[allow(clippy::derive_partial_eq_without_eq)]
            #[derive(Clone, PartialEq, ::prost::Message)]
            pub struct Shape {
                /// @@        .. cpp:var:: int64 dim (repeated)
                /// @@
                /// @@           The dimension.
                /// @@
                #[prost(int64, repeated, tag = "1")]
                pub dim: ::prost::alloc::vec::Vec<i64>,
            }
            #[allow(clippy::derive_partial_eq_without_eq)]
            #[derive(Clone, PartialEq, ::prost::Message)]
            pub struct LowerBound {
                /// @@      .. cpp:var:: int32 batch_size
                /// @@
                /// @@         The batch size of the CUDA graph. If 'max_batch_size' is 0,
                /// @@         'batch_size' must be set to 0. Otherwise, 'batch_size' must
                /// @@         be set to value between 1 and 'max_batch_size'.
                /// @@
                #[prost(int32, tag = "1")]
                pub batch_size: i32,
                /// @@      .. cpp:var:: map<string, Shape> input
                /// @@
                /// @@         The specification of the inputs. 'Shape' is the shape of
                /// @@         the input without batching dimension.
                /// @@
                #[prost(map = "string, message", tag = "2")]
                pub input: ::std::collections::HashMap<
                    ::prost::alloc::string::String,
                    Shape,
                >,
            }
        }
    }
    /// @@
    /// @@  .. cpp:var:: message ExecutionAccelerators
    /// @@
    /// @@     Specify the preferred execution accelerators to be used to execute
    /// @@     the model. Currently only recognized by ONNX Runtime backend and
    /// @@     TensorFlow backend.
    /// @@
    /// @@     For ONNX Runtime backend, it will deploy the model with the execution
    /// @@     accelerators by priority, the priority is determined based on the
    /// @@     order that they are set, i.e. the provider at the front has highest
    /// @@     priority. Overall, the priority will be in the following order:
    /// @@         <gpu_execution_accelerator> (if instance is on GPU)
    /// @@         CUDA Execution Provider     (if instance is on GPU)
    /// @@         <cpu_execution_accelerator>
    /// @@         Default CPU Execution Provider
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct ExecutionAccelerators {
        /// @@    .. cpp:var:: Accelerator gpu_execution_accelerator (repeated)
        /// @@
        /// @@       The preferred execution provider to be used if the model instance
        /// @@       is deployed on GPU.
        /// @@
        /// @@       For ONNX Runtime backend, possible value is "tensorrt" as name,
        /// @@       and no parameters are required.
        /// @@
        /// @@       For TensorFlow backend, possible values are "tensorrt",
        /// @@       "auto_mixed_precision", "gpu_io".
        /// @@
        /// @@       For "tensorrt", the following parameters can be specified:
        /// @@         "precision_mode": The precision used for optimization.
        /// @@         Allowed values are "FP32" and "FP16". Default value is "FP32".
        /// @@
        /// @@         "max_cached_engines": The maximum number of cached TensorRT
        /// @@         engines in dynamic TensorRT ops. Default value is 100.
        /// @@
        /// @@         "minimum_segment_size": The smallest model subgraph that will
        /// @@         be considered for optimization by TensorRT. Default value is 3.
        /// @@
        /// @@         "max_workspace_size_bytes": The maximum GPU memory the model
        /// @@         can use temporarily during execution. Default value is 1GB.
        /// @@
        /// @@       For "auto_mixed_precision", no parameters are required. If set,
        /// @@       the model will try to use FP16 for better performance.
        /// @@       This optimization can not be set with "tensorrt".
        /// @@
        /// @@       For "gpu_io", no parameters are required. If set, the model will
        /// @@       be executed using TensorFlow Callable API to set input and output
        /// @@       tensors in GPU memory if possible, which can reduce data transfer
        /// @@       overhead if the model is used in ensemble. However, the Callable
        /// @@       object will be created on model creation and it will request all
        /// @@       outputs for every model execution, which may impact the
        /// @@       performance if a request does not require all outputs. This
        /// @@       optimization will only take affect if the model instance is
        /// @@       created with KIND_GPU.
        /// @@
        #[prost(message, repeated, tag = "1")]
        pub gpu_execution_accelerator: ::prost::alloc::vec::Vec<
            execution_accelerators::Accelerator,
        >,
        /// @@    .. cpp:var:: Accelerator cpu_execution_accelerator (repeated)
        /// @@
        /// @@       The preferred execution provider to be used if the model instance
        /// @@       is deployed on CPU.
        /// @@
        /// @@       For ONNX Runtime backend, possible value is "openvino" as name,
        /// @@       and no parameters are required.
        /// @@
        #[prost(message, repeated, tag = "2")]
        pub cpu_execution_accelerator: ::prost::alloc::vec::Vec<
            execution_accelerators::Accelerator,
        >,
    }
    /// Nested message and enum types in `ExecutionAccelerators`.
    pub mod execution_accelerators {
        /// @@
        /// @@  .. cpp:var:: message Accelerator
        /// @@
        /// @@     Specify the accelerator to be used to execute the model.
        /// @@     Accelerator with the same name may accept different parameters
        /// @@     depending on the backends.
        /// @@
        #[allow(clippy::derive_partial_eq_without_eq)]
        #[derive(Clone, PartialEq, ::prost::Message)]
        pub struct Accelerator {
            /// @@    .. cpp:var:: string name
            /// @@
            /// @@       The name of the execution accelerator.
            /// @@
            #[prost(string, tag = "1")]
            pub name: ::prost::alloc::string::String,
            /// @@    .. cpp:var:: map<string, string> parameters
            /// @@
            /// @@       Additional paremeters used to configure the accelerator.
            /// @@
            #[prost(map = "string, string", tag = "2")]
            pub parameters: ::std::collections::HashMap<
                ::prost::alloc::string::String,
                ::prost::alloc::string::String,
            >,
        }
    }
    /// @@
    /// @@  .. cpp:var:: message PinnedMemoryBuffer
    /// @@
    /// @@     Specify whether to use a pinned memory buffer when transferring data
    /// @@     between non-pinned system memory and GPU memory. Using a pinned
    /// @@     memory buffer for system from/to GPU transfers will typically provide
    /// @@     increased performance. For example, in the common use case where the
    /// @@     request provides inputs and delivers outputs via non-pinned system
    /// @@     memory, if the model instance accepts GPU IOs, the inputs will be
    /// @@     processed by two copies: from non-pinned system memory to pinned
    /// @@     memory, and from pinned memory to GPU memory. Similarly, pinned
    /// @@     memory will be used for delivering the outputs.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct PinnedMemoryBuffer {
        /// @@    .. cpp:var:: bool enable
        /// @@
        /// @@       Use pinned memory buffer. Default is true.
        /// @@
        #[prost(bool, tag = "1")]
        pub enable: bool,
    }
    /// @@
    /// @@  .. cpp:enum:: ModelPriority
    /// @@
    /// @@     Model priorities. A model will be given scheduling and execution
    /// @@     preference over models at lower priorities. Current model
    /// @@     priorities only work for TensorRT models.
    /// @@
    #[derive(
        Clone,
        Copy,
        Debug,
        PartialEq,
        Eq,
        Hash,
        PartialOrd,
        Ord,
        ::prost::Enumeration
    )]
    #[repr(i32)]
    pub enum ModelPriority {
        /// @@    .. cpp:enumerator:: ModelPriority::PRIORITY_DEFAULT = 0
        /// @@
        /// @@       The default model priority.
        /// @@
        PriorityDefault = 0,
        /// @@    .. cpp:enumerator:: ModelPriority::PRIORITY_MAX = 1
        /// @@
        /// @@       The maximum model priority.
        /// @@
        PriorityMax = 1,
        /// @@    .. cpp:enumerator:: ModelPriority::PRIORITY_MIN = 2
        /// @@
        /// @@       The minimum model priority.
        /// @@
        PriorityMin = 2,
    }
    impl ModelPriority {
        /// String value of the enum field names used in the ProtoBuf definition.
        ///
        /// The values are not transformed in any way and thus are considered stable
        /// (if the ProtoBuf definition does not change) and safe for programmatic use.
        pub fn as_str_name(&self) -> &'static str {
            match self {
                ModelPriority::PriorityDefault => "PRIORITY_DEFAULT",
                ModelPriority::PriorityMax => "PRIORITY_MAX",
                ModelPriority::PriorityMin => "PRIORITY_MIN",
            }
        }
        /// Creates an enum from field names used in the ProtoBuf definition.
        pub fn from_str_name(value: &str) -> ::core::option::Option<Self> {
            match value {
                "PRIORITY_DEFAULT" => Some(Self::PriorityDefault),
                "PRIORITY_MAX" => Some(Self::PriorityMax),
                "PRIORITY_MIN" => Some(Self::PriorityMin),
                _ => None,
            }
        }
    }
}
/// @@
/// @@.. cpp:var:: message ModelQueuePolicy
/// @@
/// @@   Queue policy for inference requests.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelQueuePolicy {
    /// @@
    /// @@  .. cpp:var:: TimeoutAction timeout_action
    /// @@
    /// @@     The action applied to timed-out request.
    /// @@     The default action is REJECT.
    /// @@
    #[prost(enumeration = "model_queue_policy::TimeoutAction", tag = "1")]
    pub timeout_action: i32,
    /// @@
    /// @@  .. cpp:var:: uint64 default_timeout_microseconds
    /// @@
    /// @@     The default timeout for every request, in microseconds.
    /// @@     The default value is 0 which indicates that no timeout is set.
    /// @@
    #[prost(uint64, tag = "2")]
    pub default_timeout_microseconds: u64,
    /// @@
    /// @@  .. cpp:var:: bool allow_timeout_override
    /// @@
    /// @@     Whether individual request can override the default timeout value.
    /// @@     When true, individual requests can set a timeout that is less than
    /// @@     the default timeout value but may not increase the timeout.
    /// @@     The default value is false.
    /// @@
    #[prost(bool, tag = "3")]
    pub allow_timeout_override: bool,
    /// @@
    /// @@  .. cpp:var:: uint32 max_queue_size
    /// @@
    /// @@     The maximum queue size for holding requests. A request will be
    /// @@     rejected immediately if it can't be enqueued because the queue is
    /// @@     full. The default value is 0 which indicates that no maximum
    /// @@     queue size is enforced.
    /// @@
    #[prost(uint32, tag = "4")]
    pub max_queue_size: u32,
}
/// Nested message and enum types in `ModelQueuePolicy`.
pub mod model_queue_policy {
    /// @@
    /// @@  .. cpp:enum:: TimeoutAction
    /// @@
    /// @@     The action applied to timed-out requests.
    /// @@
    #[derive(
        Clone,
        Copy,
        Debug,
        PartialEq,
        Eq,
        Hash,
        PartialOrd,
        Ord,
        ::prost::Enumeration
    )]
    #[repr(i32)]
    pub enum TimeoutAction {
        /// @@    .. cpp:enumerator:: Action::REJECT = 0
        /// @@
        /// @@       Reject the request and return error message accordingly.
        /// @@
        Reject = 0,
        /// @@    .. cpp:enumerator:: Action::DELAY = 1
        /// @@
        /// @@       Delay the request until all other requests at the same
        /// @@       (or higher) priority levels that have not reached their timeouts
        /// @@       are processed. A delayed request will eventually be processed,
        /// @@       but may be delayed indefinitely due to newly arriving requests.
        /// @@
        Delay = 1,
    }
    impl TimeoutAction {
        /// String value of the enum field names used in the ProtoBuf definition.
        ///
        /// The values are not transformed in any way and thus are considered stable
        /// (if the ProtoBuf definition does not change) and safe for programmatic use.
        pub fn as_str_name(&self) -> &'static str {
            match self {
                TimeoutAction::Reject => "REJECT",
                TimeoutAction::Delay => "DELAY",
            }
        }
        /// Creates an enum from field names used in the ProtoBuf definition.
        pub fn from_str_name(value: &str) -> ::core::option::Option<Self> {
            match value {
                "REJECT" => Some(Self::Reject),
                "DELAY" => Some(Self::Delay),
                _ => None,
            }
        }
    }
}
/// @@
/// @@.. cpp:var:: message ModelDynamicBatching
/// @@
/// @@   Dynamic batching configuration. These settings control how dynamic
/// @@   batching operates for the model.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelDynamicBatching {
    /// @@  .. cpp:var:: int32 preferred_batch_size (repeated)
    /// @@
    /// @@     Preferred batch sizes for dynamic batching. If a batch of one of
    /// @@     these sizes can be formed it will be executed immediately.  If
    /// @@     not specified a preferred batch size will be chosen automatically
    /// @@     based on model and GPU characteristics.
    /// @@
    #[prost(int32, repeated, tag = "1")]
    pub preferred_batch_size: ::prost::alloc::vec::Vec<i32>,
    /// @@  .. cpp:var:: uint64 max_queue_delay_microseconds
    /// @@
    /// @@     The maximum time, in microseconds, a request will be delayed in
    /// @@     the scheduling queue to wait for additional requests for
    /// @@     batching. Default is 0.
    /// @@
    #[prost(uint64, tag = "2")]
    pub max_queue_delay_microseconds: u64,
    /// @@  .. cpp:var:: bool preserve_ordering
    /// @@
    /// @@     Should the dynamic batcher preserve the ordering of responses to
    /// @@     match the order of requests received by the scheduler. Default is
    /// @@     false. If true, the responses will be returned in the same order as
    /// @@     the order of requests sent to the scheduler. If false, the responses
    /// @@     may be returned in arbitrary order. This option is specifically
    /// @@     needed when a sequence of related inference requests (i.e. inference
    /// @@     requests with the same correlation ID) are sent to the dynamic
    /// @@     batcher to ensure that the sequence responses are in the correct
    /// @@     order.
    /// @@
    #[prost(bool, tag = "3")]
    pub preserve_ordering: bool,
    /// @@  .. cpp:var:: uint32 priority_levels
    /// @@
    /// @@     The number of priority levels to be enabled for the model,
    /// @@     the priority level starts from 1 and 1 is the highest priority.
    /// @@     Requests are handled in priority order with all priority 1 requests
    /// @@     processed before priority 2, all priority 2 requests processed before
    /// @@     priority 3, etc. Requests with the same priority level will be
    /// @@     handled in the order that they are received.
    /// @@
    #[prost(uint32, tag = "4")]
    pub priority_levels: u32,
    /// @@  .. cpp:var:: uint32 default_priority_level
    /// @@
    /// @@     The priority level used for requests that don't specify their
    /// @@     priority. The value must be in the range [ 1, 'priority_levels' ].
    /// @@
    #[prost(uint32, tag = "5")]
    pub default_priority_level: u32,
    /// @@  .. cpp:var:: ModelQueuePolicy default_queue_policy
    /// @@
    /// @@     The default queue policy used for requests that don't require
    /// @@     priority handling and requests that specify priority levels where
    /// @@     there is no specific policy given. If not specified, a policy with
    /// @@     default field values will be used.
    /// @@
    #[prost(message, optional, tag = "6")]
    pub default_queue_policy: ::core::option::Option<ModelQueuePolicy>,
    /// @@  .. cpp:var:: map<uint32, ModelQueuePolicy> priority_queue_policy
    /// @@
    /// @@     Specify the queue policy for the priority level. The default queue
    /// @@     policy will be used if a priority level doesn't specify a queue
    /// @@     policy.
    /// @@
    #[prost(map = "uint32, message", tag = "7")]
    pub priority_queue_policy: ::std::collections::HashMap<u32, ModelQueuePolicy>,
}
/// @@
/// @@.. cpp:var:: message ModelSequenceBatching
/// @@
/// @@   Sequence batching configuration. These settings control how sequence
/// @@   batching operates for the model.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelSequenceBatching {
    /// @@  .. cpp:var:: uint64 max_sequence_idle_microseconds
    /// @@
    /// @@     The maximum time, in microseconds, that a sequence is allowed to
    /// @@     be idle before it is aborted. The inference server considers a
    /// @@     sequence idle when it does not have any inference request queued
    /// @@     for the sequence. If this limit is exceeded, the inference server
    /// @@     will free the sequence slot allocated by the sequence and make it
    /// @@     available for another sequence. If not specified (or specified as
    /// @@     zero) a default value of 1000000 (1 second) is used.
    /// @@
    #[prost(uint64, tag = "1")]
    pub max_sequence_idle_microseconds: u64,
    /// @@  .. cpp:var:: ControlInput control_input (repeated)
    /// @@
    /// @@     The model input(s) that the server should use to communicate
    /// @@     sequence start, stop, ready and similar control values to the
    /// @@     model.
    /// @@
    #[prost(message, repeated, tag = "2")]
    pub control_input: ::prost::alloc::vec::Vec<model_sequence_batching::ControlInput>,
    /// @@  .. cpp:var:: State state (repeated)
    /// @@
    /// @@     The optional state that can be stored in Triton for performing
    /// @@     inference requests on a sequence. Each sequence holds an implicit
    /// @@     state local to itself. The output state tensor provided by the
    /// @@     model in 'output_name' field of the current inference request will
    /// @@     be transferred as an input tensor named 'input_name' in the next
    /// @@     request of the same sequence. The input state of the first request
    /// @@     in the sequence contains garbage data.
    /// @@
    #[prost(message, repeated, tag = "5")]
    pub state: ::prost::alloc::vec::Vec<model_sequence_batching::State>,
    /// @@  .. cpp:var:: oneof strategy_choice
    /// @@
    /// @@     The strategy used by the sequence batcher. Default strategy
    /// @@     is 'direct'.
    /// @@
    #[prost(oneof = "model_sequence_batching::StrategyChoice", tags = "3, 4")]
    pub strategy_choice: ::core::option::Option<model_sequence_batching::StrategyChoice>,
}
/// Nested message and enum types in `ModelSequenceBatching`.
pub mod model_sequence_batching {
    /// @@  .. cpp:var:: message Control
    /// @@
    /// @@     A control is a signal that the sequence batcher uses to
    /// @@     communicate with a backend.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct Control {
        /// @@    .. cpp:var:: Kind kind
        /// @@
        /// @@       The kind of this control.
        /// @@
        #[prost(enumeration = "control::Kind", tag = "1")]
        pub kind: i32,
        /// @@    .. cpp:var:: int32 int32_false_true (repeated)
        /// @@
        /// @@       The control's true and false setting is indicated by setting
        /// @@       a value in an int32 tensor. The tensor must be a
        /// @@       1-dimensional tensor with size equal to the batch size of
        /// @@       the request. 'int32_false_true' must have two entries: the
        /// @@       first the false value and the second the true value.
        /// @@
        #[prost(int32, repeated, tag = "2")]
        pub int32_false_true: ::prost::alloc::vec::Vec<i32>,
        /// @@    .. cpp:var:: float fp32_false_true (repeated)
        /// @@
        /// @@       The control's true and false setting is indicated by setting
        /// @@       a value in a fp32 tensor. The tensor must be a
        /// @@       1-dimensional tensor with size equal to the batch size of
        /// @@       the request. 'fp32_false_true' must have two entries: the
        /// @@       first the false value and the second the true value.
        /// @@
        #[prost(float, repeated, tag = "3")]
        pub fp32_false_true: ::prost::alloc::vec::Vec<f32>,
        /// @@    .. cpp:var:: bool bool_false_true (repeated)
        /// @@
        /// @@       The control's true and false setting is indicated by setting
        /// @@       a value in a bool tensor. The tensor must be a
        /// @@       1-dimensional tensor with size equal to the batch size of
        /// @@       the request. 'bool_false_true' must have two entries: the
        /// @@       first the false value and the second the true value.
        /// @@
        #[prost(bool, repeated, tag = "5")]
        pub bool_false_true: ::prost::alloc::vec::Vec<bool>,
        /// @@    .. cpp:var:: DataType data_type
        /// @@
        /// @@       The control's datatype.
        /// @@
        #[prost(enumeration = "super::DataType", tag = "4")]
        pub data_type: i32,
    }
    /// Nested message and enum types in `Control`.
    pub mod control {
        /// @@
        /// @@    .. cpp:enum:: Kind
        /// @@
        /// @@       The kind of the control.
        /// @@
        #[derive(
            Clone,
            Copy,
            Debug,
            PartialEq,
            Eq,
            Hash,
            PartialOrd,
            Ord,
            ::prost::Enumeration
        )]
        #[repr(i32)]
        pub enum Kind {
            /// @@      .. cpp:enumerator:: Kind::CONTROL_SEQUENCE_START = 0
            /// @@
            /// @@         A new sequence is/is-not starting. If true a sequence is
            /// @@         starting, if false a sequence is continuing. Must
            /// @@         specify either int32_false_true, fp32_false_true or
            /// @@         bool_false_true for this control. This control is optional.
            /// @@
            ControlSequenceStart = 0,
            /// @@      .. cpp:enumerator:: Kind::CONTROL_SEQUENCE_READY = 1
            /// @@
            /// @@         A sequence is/is-not ready for inference. If true the
            /// @@         input tensor data is valid and should be used. If false
            /// @@         the input tensor data is invalid and inferencing should
            /// @@         be "skipped". Must specify either int32_false_true,
            /// @@         fp32_false_true or bool_false_true for this control. This
            /// @@         control is optional.
            /// @@
            ControlSequenceReady = 1,
            /// @@      .. cpp:enumerator:: Kind::CONTROL_SEQUENCE_END = 2
            /// @@
            /// @@         A sequence is/is-not ending. If true a sequence is
            /// @@         ending, if false a sequence is continuing. Must specify
            /// @@         either int32_false_true, fp32_false_true or bool_false_true
            /// @@         for this control. This control is optional.
            /// @@
            ControlSequenceEnd = 2,
            /// @@      .. cpp:enumerator:: Kind::CONTROL_SEQUENCE_CORRID = 3
            /// @@
            /// @@         The correlation ID of the sequence. The correlation ID
            /// @@         is an uint64_t value that is communicated in whole or
            /// @@         in part by the tensor. The tensor's datatype must be
            /// @@         specified by data_type and must be TYPE_UINT64, TYPE_INT64,
            /// @@         TYPE_UINT32 or TYPE_INT32. If a 32-bit datatype is specified
            /// @@         the correlation ID will be truncated to the low-order 32
            /// @@         bits. This control is optional.
            /// @@
            ControlSequenceCorrid = 3,
        }
        impl Kind {
            /// String value of the enum field names used in the ProtoBuf definition.
            ///
            /// The values are not transformed in any way and thus are considered stable
            /// (if the ProtoBuf definition does not change) and safe for programmatic use.
            pub fn as_str_name(&self) -> &'static str {
                match self {
                    Kind::ControlSequenceStart => "CONTROL_SEQUENCE_START",
                    Kind::ControlSequenceReady => "CONTROL_SEQUENCE_READY",
                    Kind::ControlSequenceEnd => "CONTROL_SEQUENCE_END",
                    Kind::ControlSequenceCorrid => "CONTROL_SEQUENCE_CORRID",
                }
            }
            /// Creates an enum from field names used in the ProtoBuf definition.
            pub fn from_str_name(value: &str) -> ::core::option::Option<Self> {
                match value {
                    "CONTROL_SEQUENCE_START" => Some(Self::ControlSequenceStart),
                    "CONTROL_SEQUENCE_READY" => Some(Self::ControlSequenceReady),
                    "CONTROL_SEQUENCE_END" => Some(Self::ControlSequenceEnd),
                    "CONTROL_SEQUENCE_CORRID" => Some(Self::ControlSequenceCorrid),
                    _ => None,
                }
            }
        }
    }
    /// @@  .. cpp:var:: message ControlInput
    /// @@
    /// @@     The sequence control values to communicate by a model input.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct ControlInput {
        /// @@    .. cpp:var:: string name
        /// @@
        /// @@       The name of the model input.
        /// @@
        #[prost(string, tag = "1")]
        pub name: ::prost::alloc::string::String,
        /// @@    .. cpp:var:: Control control (repeated)
        /// @@
        /// @@       The control value(s) that should be communicated to the
        /// @@       model using this model input.
        /// @@
        #[prost(message, repeated, tag = "2")]
        pub control: ::prost::alloc::vec::Vec<Control>,
    }
    /// @@
    /// @@  .. cpp:var:: message InitialState
    /// @@
    /// @@     Settings used to initialize data for implicit state.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct InitialState {
        /// @@      .. cpp:var:: DataType data_type
        /// @@
        /// @@         The data-type of the state.
        /// @@
        #[prost(enumeration = "super::DataType", tag = "1")]
        pub data_type: i32,
        /// @@      .. cpp:var:: int64 dims (repeated)
        /// @@
        /// @@         The shape of the state tensor, not including the batch
        /// @@         dimension.
        /// @@
        #[prost(int64, repeated, tag = "2")]
        pub dims: ::prost::alloc::vec::Vec<i64>,
        /// @@  .. cpp:var:: string name
        /// @@
        /// @@     The name of the state initialization.
        /// @@
        #[prost(string, tag = "5")]
        pub name: ::prost::alloc::string::String,
        /// @@      .. cpp:var:: oneof state_data
        /// @@
        /// @@         Specify how the initial state data is generated.
        /// @@
        #[prost(oneof = "initial_state::StateData", tags = "3, 4")]
        pub state_data: ::core::option::Option<initial_state::StateData>,
    }
    /// Nested message and enum types in `InitialState`.
    pub mod initial_state {
        /// @@      .. cpp:var:: oneof state_data
        /// @@
        /// @@         Specify how the initial state data is generated.
        /// @@
        #[allow(clippy::derive_partial_eq_without_eq)]
        #[derive(Clone, PartialEq, ::prost::Oneof)]
        pub enum StateData {
            /// @@
            /// @@      .. cpp:var:: bool zero_data
            /// @@
            /// @@         The identifier for using zeros as initial state data.
            /// @@         Note that the value of 'zero_data' will not be checked,
            /// @@         instead, zero data will be used as long as the field is set.
            /// @@
            #[prost(bool, tag = "3")]
            ZeroData(bool),
            /// @@      .. cpp:var:: string data_file
            /// @@
            /// @@         The file whose content will be used as the initial data for
            /// @@         the state in row-major order. The file must be provided in
            /// @@         sub-directory 'initial_state' under the model directory.
            /// @@
            #[prost(string, tag = "4")]
            DataFile(::prost::alloc::string::String),
        }
    }
    /// @@  .. cpp:var:: message State
    /// @@
    /// @@     An input / output pair of tensors that carry state for the sequence.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct State {
        /// @@    .. cpp:var:: string input_name
        /// @@
        /// @@       The name of the model state input.
        /// @@
        #[prost(string, tag = "1")]
        pub input_name: ::prost::alloc::string::String,
        /// @@    .. cpp:var:: string output_name
        /// @@
        /// @@       The name of the model state output.
        /// @@
        #[prost(string, tag = "2")]
        pub output_name: ::prost::alloc::string::String,
        /// @@    .. cpp:var:: DataType data_type
        /// @@
        /// @@       The data-type of the state.
        /// @@
        #[prost(enumeration = "super::DataType", tag = "3")]
        pub data_type: i32,
        /// @@    .. cpp:var:: int64 dim (repeated)
        /// @@
        /// @@       The dimension.
        /// @@
        #[prost(int64, repeated, tag = "4")]
        pub dims: ::prost::alloc::vec::Vec<i64>,
        /// @@  .. cpp:var:: InitialState initial_state (repeated)
        /// @@
        /// @@     The optional field to specify the initial state for the model.
        /// @@
        #[prost(message, repeated, tag = "5")]
        pub initial_state: ::prost::alloc::vec::Vec<InitialState>,
    }
    /// @@  .. cpp:var:: message StrategyDirect
    /// @@
    /// @@     The sequence batcher uses a specific, unique batch
    /// @@     slot for each sequence. All inference requests in a
    /// @@     sequence are directed to the same batch slot in the same
    /// @@     model instance over the lifetime of the sequence. This
    /// @@     is the default strategy.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct StrategyDirect {
        /// @@    .. cpp:var:: uint64 max_queue_delay_microseconds
        /// @@
        /// @@       The maximum time, in microseconds, a candidate request
        /// @@       will be delayed in the sequence batch scheduling queue to
        /// @@       wait for additional requests for batching. Default is 0.
        /// @@
        #[prost(uint64, tag = "1")]
        pub max_queue_delay_microseconds: u64,
        /// @@    .. cpp:var:: float minimum_slot_utilization
        /// @@
        /// @@       The minimum slot utilization that must be satisfied to
        /// @@       execute the batch before 'max_queue_delay_microseconds' expires.
        /// @@       For example, a value of 0.5 indicates that the batch should be
        /// @@       executed as soon as 50% or more of the slots are ready even if
        /// @@       the 'max_queue_delay_microseconds' timeout has not expired.
        /// @@       The default is 0.0, indicating that a batch will be executed
        /// @@       before 'max_queue_delay_microseconds' timeout expires if at least
        /// @@       one batch slot is ready. 'max_queue_delay_microseconds' will be
        /// @@       ignored unless minimum_slot_utilization is set to a non-zero
        /// @@       value.
        /// @@
        #[prost(float, tag = "2")]
        pub minimum_slot_utilization: f32,
    }
    /// @@  .. cpp:var:: message StrategyOldest
    /// @@
    /// @@     The sequence batcher maintains up to 'max_candidate_sequences'
    /// @@     candidate sequences. 'max_candidate_sequences' can be greater
    /// @@     than the model's 'max_batch_size'. For inferencing the batcher
    /// @@     chooses from the candidate sequences up to 'max_batch_size'
    /// @@     inference requests. Requests are chosen in an oldest-first
    /// @@     manner across all candidate sequences. A given sequence is
    /// @@     not guaranteed to be assigned to the same batch slot for
    /// @@     all inference requests of that sequence.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct StrategyOldest {
        /// @@    .. cpp:var:: int32 max_candidate_sequences
        /// @@
        /// @@       Maximum number of candidate sequences that the batcher
        /// @@       maintains. Excess seqences are kept in an ordered backlog
        /// @@       and become candidates when existing candidate sequences
        /// @@       complete.
        /// @@
        #[prost(int32, tag = "1")]
        pub max_candidate_sequences: i32,
        /// @@    .. cpp:var:: int32 preferred_batch_size (repeated)
        /// @@
        /// @@       Preferred batch sizes for dynamic batching of candidate
        /// @@       sequences. If a batch of one of these sizes can be formed
        /// @@       it will be executed immediately. If not specified a
        /// @@       preferred batch size will be chosen automatically
        /// @@       based on model and GPU characteristics.
        /// @@
        #[prost(int32, repeated, tag = "2")]
        pub preferred_batch_size: ::prost::alloc::vec::Vec<i32>,
        /// @@    .. cpp:var:: uint64 max_queue_delay_microseconds
        /// @@
        /// @@       The maximum time, in microseconds, a candidate request
        /// @@       will be delayed in the dynamic batch scheduling queue to
        /// @@       wait for additional requests for batching. Default is 0.
        /// @@
        #[prost(uint64, tag = "3")]
        pub max_queue_delay_microseconds: u64,
    }
    /// @@  .. cpp:var:: oneof strategy_choice
    /// @@
    /// @@     The strategy used by the sequence batcher. Default strategy
    /// @@     is 'direct'.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Oneof)]
    pub enum StrategyChoice {
        /// @@    .. cpp:var:: StrategyDirect direct
        /// @@
        /// @@       StrategyDirect scheduling strategy.
        /// @@
        #[prost(message, tag = "3")]
        Direct(StrategyDirect),
        /// @@    .. cpp:var:: StrategyOldest oldest
        /// @@
        /// @@       StrategyOldest scheduling strategy.
        /// @@
        #[prost(message, tag = "4")]
        Oldest(StrategyOldest),
    }
}
/// @@
/// @@.. cpp:var:: message ModelEnsembling
/// @@
/// @@   Model ensembling configuration. These settings specify the models that
/// @@   compose the ensemble and how data flows between the models.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelEnsembling {
    /// @@  .. cpp:var:: Step step (repeated)
    /// @@
    /// @@     The models and the input / output mappings used within the ensemble.
    /// @@
    #[prost(message, repeated, tag = "1")]
    pub step: ::prost::alloc::vec::Vec<model_ensembling::Step>,
}
/// Nested message and enum types in `ModelEnsembling`.
pub mod model_ensembling {
    /// @@  .. cpp:var:: message Step
    /// @@
    /// @@     Each step specifies a model included in the ensemble,
    /// @@     maps ensemble tensor names to the model input tensors,
    /// @@     and maps model output tensors to ensemble tensor names
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct Step {
        /// @@  .. cpp:var:: string model_name
        /// @@
        /// @@     The name of the model to execute for this step of the ensemble.
        /// @@
        #[prost(string, tag = "1")]
        pub model_name: ::prost::alloc::string::String,
        /// @@  .. cpp:var:: int64 model_version
        /// @@
        /// @@     The version of the model to use for inference. If -1
        /// @@     the latest/most-recent version of the model is used.
        /// @@
        #[prost(int64, tag = "2")]
        pub model_version: i64,
        /// @@  .. cpp:var:: map<string,string> input_map
        /// @@
        /// @@     Map from name of an input tensor on this step's model to ensemble
        /// @@     tensor name. The ensemble tensor must have the same data type and
        /// @@     shape as the model input. Each model input must be assigned to
        /// @@     one ensemble tensor, but the same ensemble tensor can be assigned
        /// @@     to multiple model inputs.
        /// @@
        #[prost(map = "string, string", tag = "3")]
        pub input_map: ::std::collections::HashMap<
            ::prost::alloc::string::String,
            ::prost::alloc::string::String,
        >,
        /// @@  .. cpp:var:: map<string,string> output_map
        /// @@
        /// @@     Map from name of an output tensor on this step's model to ensemble
        /// @@     tensor name. The data type and shape of the ensemble tensor will
        /// @@     be inferred from the model output. It is optional to assign all
        /// @@     model outputs to ensemble tensors. One ensemble tensor name
        /// @@     can appear in an output map only once.
        /// @@
        #[prost(map = "string, string", tag = "4")]
        pub output_map: ::std::collections::HashMap<
            ::prost::alloc::string::String,
            ::prost::alloc::string::String,
        >,
    }
}
/// @@
/// @@.. cpp:var:: message ModelParameter
/// @@
/// @@   A model parameter.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelParameter {
    /// @@  .. cpp:var:: string string_value
    /// @@
    /// @@     The string value of the parameter.
    /// @@
    #[prost(string, tag = "1")]
    pub string_value: ::prost::alloc::string::String,
}
/// @@
/// @@.. cpp:var:: message ModelWarmup
/// @@
/// @@   Settings used to construct the request sample for model warmup.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelWarmup {
    /// @@  .. cpp:var:: string name
    /// @@
    /// @@     The name of the request sample.
    /// @@
    #[prost(string, tag = "1")]
    pub name: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: uint32 batch_size
    /// @@
    /// @@     The batch size of the inference request. This must be >= 1. For
    /// @@     models that don't support batching, batch_size must be 1. If
    /// @@     batch_size > 1, the 'inputs' specified below will be duplicated to
    /// @@     match the batch size requested.
    /// @@
    #[prost(uint32, tag = "2")]
    pub batch_size: u32,
    /// @@  .. cpp:var:: map<string, Input> inputs
    /// @@
    /// @@     The warmup meta data associated with every model input, including
    /// @@     control tensors.
    /// @@
    #[prost(map = "string, message", tag = "3")]
    pub inputs: ::std::collections::HashMap<
        ::prost::alloc::string::String,
        model_warmup::Input,
    >,
    /// @@  .. cpp:var:: uint32 count
    /// @@
    /// @@     The number of iterations that this warmup sample will be executed.
    /// @@     For example, if this field is set to 2, 2 model executions using this
    /// @@     sample will be scheduled for warmup. Default value is 0 which
    /// @@     indicates that this sample will be used only once.
    /// @@     Note that for sequence model, 'count' may not work well
    /// @@     because the model often expect a valid sequence of requests which
    /// @@     should be represented by a series of warmup samples. 'count > 1'
    /// @@     essentially "resends" one of the sample, which may invalidate the
    /// @@     sequence and result in unexpected warmup failure.
    /// @@
    #[prost(uint32, tag = "4")]
    pub count: u32,
}
/// Nested message and enum types in `ModelWarmup`.
pub mod model_warmup {
    /// @@
    /// @@  .. cpp:var:: message Input
    /// @@
    /// @@     Meta data associated with an input.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct Input {
        /// @@    .. cpp:var:: DataType data_type
        /// @@
        /// @@       The data-type of the input.
        /// @@
        #[prost(enumeration = "super::DataType", tag = "1")]
        pub data_type: i32,
        /// @@    .. cpp:var:: int64 dims (repeated)
        /// @@
        /// @@       The shape of the input tensor, not including the batch dimension.
        /// @@
        #[prost(int64, repeated, tag = "2")]
        pub dims: ::prost::alloc::vec::Vec<i64>,
        /// @@    .. cpp:var:: oneof input_data_type
        /// @@
        /// @@       Specify how the input data is generated. If the input has STRING
        /// @@       data type and 'random_data' is set, the data generation will fall
        /// @@       back to 'zero_data'.
        /// @@
        #[prost(oneof = "input::InputDataType", tags = "3, 4, 5")]
        pub input_data_type: ::core::option::Option<input::InputDataType>,
    }
    /// Nested message and enum types in `Input`.
    pub mod input {
        /// @@    .. cpp:var:: oneof input_data_type
        /// @@
        /// @@       Specify how the input data is generated. If the input has STRING
        /// @@       data type and 'random_data' is set, the data generation will fall
        /// @@       back to 'zero_data'.
        /// @@
        #[allow(clippy::derive_partial_eq_without_eq)]
        #[derive(Clone, PartialEq, ::prost::Oneof)]
        pub enum InputDataType {
            /// @@
            /// @@    .. cpp:var:: bool zero_data
            /// @@
            /// @@       The identifier for using zeros as input data. Note that the
            /// @@       value of 'zero_data' will not be checked, instead, zero data
            /// @@       will be used as long as the field is set.
            /// @@
            #[prost(bool, tag = "3")]
            ZeroData(bool),
            /// @@
            /// @@    .. cpp:var:: bool random_data
            /// @@
            /// @@       The identifier for using random data as input data. Note that
            /// @@       the value of 'random_data' will not be checked, instead,
            /// @@       random data will be used as long as the field is set.
            /// @@
            #[prost(bool, tag = "4")]
            RandomData(bool),
            /// @@    .. cpp:var:: string input_data_file
            /// @@
            /// @@       The file whose content will be used as raw input data in
            /// @@       row-major order. The file must be provided in a sub-directory
            /// @@       'warmup' under the model directory. The file contents should be
            /// @@       in binary format. For TYPE_STRING data-type, an element is
            /// @@       represented by a 4-byte unsigned integer giving the length
            /// @@       followed by the actual bytes.
            /// @@
            #[prost(string, tag = "5")]
            InputDataFile(::prost::alloc::string::String),
        }
    }
}
/// @@
/// @@ .. cpp:var:: message ModelOperations
/// @@
/// @@    The metadata of libraries providing custom operations for this model.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelOperations {
    /// @@  .. cpp:var:: string op_library_filename (repeated)
    /// @@
    /// @@     Optional paths of the libraries providing custom operations for
    /// @@     this model. Valid only for ONNX models.
    /// @@
    #[prost(string, repeated, tag = "1")]
    pub op_library_filename: ::prost::alloc::vec::Vec<::prost::alloc::string::String>,
}
/// @@
/// @@ .. cpp:var:: message ModelTransactionPolicy
/// @@
/// @@    The specification that describes the nature of transactions
/// @@    to be expected from the model.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelTransactionPolicy {
    /// @@  .. cpp:var:: bool decoupled
    /// @@
    /// @@     Indicates whether responses generated by the model are decoupled with
    /// @@     the requests issued to it, which means the number of responses
    /// @@     generated by model may differ from number of requests issued, and
    /// @@     that the responses may be out of order relative to the order of
    /// @@     requests. The default is false, which means the model will generate
    /// @@     exactly one response for each request.
    /// @@
    #[prost(bool, tag = "1")]
    pub decoupled: bool,
}
/// @@
/// @@.. cpp:var:: message ModelRepositoryAgents
/// @@
/// @@   The repository agents for the model.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelRepositoryAgents {
    /// @@
    /// @@  .. cpp:var:: Agent agents (repeated)
    /// @@
    /// @@     The ordered list of agents for the model. These agents will be
    /// @@     invoked in order to respond to repository actions occuring for the
    /// @@     model.
    /// @@
    #[prost(message, repeated, tag = "1")]
    pub agents: ::prost::alloc::vec::Vec<model_repository_agents::Agent>,
}
/// Nested message and enum types in `ModelRepositoryAgents`.
pub mod model_repository_agents {
    /// @@
    /// @@  .. cpp:var:: message Agent
    /// @@
    /// @@     A repository agent that should be invoked for the specified
    /// @@     repository actions for this model.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct Agent {
        /// @@    .. cpp:var:: string name
        /// @@
        /// @@       The name of the agent.
        /// @@
        #[prost(string, tag = "1")]
        pub name: ::prost::alloc::string::String,
        /// @@    .. cpp:var:: map<string, string> parameters
        /// @@
        /// @@       The parameters for the agent.
        /// @@
        #[prost(map = "string, string", tag = "2")]
        pub parameters: ::std::collections::HashMap<
            ::prost::alloc::string::String,
            ::prost::alloc::string::String,
        >,
    }
}
/// @@
/// @@.. cpp:var:: message ModelResponseCache
/// @@
/// @@   The response cache setting for the model.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelResponseCache {
    /// @@
    /// @@  .. cpp::var:: bool enable
    /// @@
    /// @@     Whether or not to use response cache for the model. If True, the
    /// @@     responses from the model are cached and when identical request
    /// @@     is encountered, instead of going through the model execution,
    /// @@     the response from the cache is utilized. By default, response
    /// @@     cache is disabled for the models.
    /// @@
    #[prost(bool, tag = "1")]
    pub enable: bool,
}
/// @@
/// @@.. cpp:var:: message ModelConfig
/// @@
/// @@   A model configuration.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelConfig {
    /// @@  .. cpp:var:: string name
    /// @@
    /// @@     The name of the model.
    /// @@
    #[prost(string, tag = "1")]
    pub name: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: string platform
    /// @@
    /// @@     The framework for the model. Possible values are
    /// @@     "tensorrt_plan", "tensorflow_graphdef",
    /// @@     "tensorflow_savedmodel", "onnxruntime_onnx",
    /// @@     "pytorch_libtorch".
    /// @@
    #[prost(string, tag = "2")]
    pub platform: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: string backend
    /// @@
    /// @@     The backend used by the model.
    /// @@
    #[prost(string, tag = "17")]
    pub backend: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: ModelVersionPolicy version_policy
    /// @@
    /// @@     Policy indicating which version(s) of the model will be served.
    /// @@
    #[prost(message, optional, tag = "3")]
    pub version_policy: ::core::option::Option<ModelVersionPolicy>,
    /// @@  .. cpp:var:: int32 max_batch_size
    /// @@
    /// @@     Maximum batch size allowed for inference. This can only decrease
    /// @@     what is allowed by the model itself. A max_batch_size value of 0
    /// @@     indicates that batching is not allowed for the model and the
    /// @@     dimension/shape of the input and output tensors must exactly
    /// @@     match what is specified in the input and output configuration. A
    /// @@     max_batch_size value > 0 indicates that batching is allowed and
    /// @@     so the model expects the input tensors to have an additional
    /// @@     initial dimension for the batching that is not specified in the
    /// @@     input (for example, if the model supports batched inputs of
    /// @@     2-dimensional tensors then the model configuration will specify
    /// @@     the input shape as [ X, Y ] but the model will expect the actual
    /// @@     input tensors to have shape [ N, X, Y ]). For max_batch_size > 0
    /// @@     returned outputs will also have an additional initial dimension
    /// @@     for the batch.
    /// @@
    #[prost(int32, tag = "4")]
    pub max_batch_size: i32,
    /// @@  .. cpp:var:: ModelInput input (repeated)
    /// @@
    /// @@     The inputs request by the model.
    /// @@
    #[prost(message, repeated, tag = "5")]
    pub input: ::prost::alloc::vec::Vec<ModelInput>,
    /// @@  .. cpp:var:: ModelOutput output (repeated)
    /// @@
    /// @@     The outputs produced by the model.
    /// @@
    #[prost(message, repeated, tag = "6")]
    pub output: ::prost::alloc::vec::Vec<ModelOutput>,
    /// @@  .. cpp:var:: BatchInput batch_input (repeated)
    /// @@
    /// @@     The model input(s) that the server should use to communicate
    /// @@     batch related values to the model.
    /// @@
    #[prost(message, repeated, tag = "20")]
    pub batch_input: ::prost::alloc::vec::Vec<BatchInput>,
    /// @@  .. cpp:var:: BatchOutput batch_output (repeated)
    /// @@
    /// @@     The outputs produced by the model that requires special handling
    /// @@     by the model backend.
    /// @@
    #[prost(message, repeated, tag = "21")]
    pub batch_output: ::prost::alloc::vec::Vec<BatchOutput>,
    /// @@  .. cpp:var:: ModelOptimizationPolicy optimization
    /// @@
    /// @@     Optimization configuration for the model. If not specified
    /// @@     then default optimization policy is used.
    /// @@
    #[prost(message, optional, tag = "12")]
    pub optimization: ::core::option::Option<ModelOptimizationPolicy>,
    /// @@  .. cpp:var:: ModelInstanceGroup instance_group (repeated)
    /// @@
    /// @@     Instances of this model. If not specified, one instance
    /// @@     of the model will be instantiated on each available GPU.
    /// @@
    #[prost(message, repeated, tag = "7")]
    pub instance_group: ::prost::alloc::vec::Vec<ModelInstanceGroup>,
    /// @@  .. cpp:var:: string default_model_filename
    /// @@
    /// @@     Optional filename of the model file to use if a
    /// @@     compute-capability specific model is not specified in
    /// @@     :cpp:var:`cc_model_filenames`. If not specified the default name
    /// @@     is 'model.graphdef', 'model.savedmodel', 'model.plan' or
    /// @@     'model.pt' depending on the model type.
    /// @@
    #[prost(string, tag = "8")]
    pub default_model_filename: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: map<string,string> cc_model_filenames
    /// @@
    /// @@     Optional map from CUDA compute capability to the filename of
    /// @@     the model that supports that compute capability. The filename
    /// @@     refers to a file within the model version directory.
    /// @@
    #[prost(map = "string, string", tag = "9")]
    pub cc_model_filenames: ::std::collections::HashMap<
        ::prost::alloc::string::String,
        ::prost::alloc::string::String,
    >,
    /// @@  .. cpp:var:: map<string,string> metric_tags
    /// @@
    /// @@     Optional metric tags. User-specific key-value pairs for metrics
    /// @@     reported for this model. These tags are applied to the metrics
    /// @@     reported on the HTTP metrics port.
    /// @@
    #[prost(map = "string, string", tag = "10")]
    pub metric_tags: ::std::collections::HashMap<
        ::prost::alloc::string::String,
        ::prost::alloc::string::String,
    >,
    /// @@  .. cpp:var:: map<string,ModelParameter> parameters
    /// @@
    /// @@     Optional model parameters. User-specified parameter values.
    /// @@
    #[prost(map = "string, message", tag = "14")]
    pub parameters: ::std::collections::HashMap<
        ::prost::alloc::string::String,
        ModelParameter,
    >,
    /// @@  .. cpp:var:: ModelWarmup model_warmup (repeated)
    /// @@
    /// @@     Warmup setting of this model. If specified, all instances
    /// @@     will be run with the request samples in sequence before
    /// @@     serving the model.
    /// @@     This field can only be specified if the model is not an ensemble
    /// @@     model.
    /// @@
    #[prost(message, repeated, tag = "16")]
    pub model_warmup: ::prost::alloc::vec::Vec<ModelWarmup>,
    /// @@  .. cpp:var:: ModelOperations model_operations
    /// @@
    /// @@     Optional metadata of the libraries providing custom operations for
    /// @@     this model.
    /// @@
    #[prost(message, optional, tag = "18")]
    pub model_operations: ::core::option::Option<ModelOperations>,
    /// @@  .. cpp:var:: ModelTransactionPolicy model_transaction_policy
    /// @@
    /// @@     Optional specification that describes the nature of transactions
    /// @@     to be expected from the model.
    /// @@
    #[prost(message, optional, tag = "19")]
    pub model_transaction_policy: ::core::option::Option<ModelTransactionPolicy>,
    /// @@  .. cpp:var:: ModelRepositoryAgents model_repository_agents
    /// @@
    /// @@     Optional specification of the agent(s) that should be invoked
    /// @@     with repository actions are performed for this model.
    /// @@
    #[prost(message, optional, tag = "23")]
    pub model_repository_agents: ::core::option::Option<ModelRepositoryAgents>,
    /// @@  .. cpp:var:: ModelResponseCache response_cache
    /// @@
    /// @@     Optional setting for utilizing the response cache for this
    /// @@     model.
    /// @@
    #[prost(message, optional, tag = "24")]
    pub response_cache: ::core::option::Option<ModelResponseCache>,
    /// @@  .. cpp:var:: oneof scheduling_choice
    /// @@
    /// @@     The scheduling policy for the model. If not specified the
    /// @@     default scheduling policy is used for the model. The default
    /// @@     policy is to execute each inference request independently.
    /// @@
    #[prost(oneof = "model_config::SchedulingChoice", tags = "11, 13, 15")]
    pub scheduling_choice: ::core::option::Option<model_config::SchedulingChoice>,
}
/// Nested message and enum types in `ModelConfig`.
pub mod model_config {
    /// @@  .. cpp:var:: oneof scheduling_choice
    /// @@
    /// @@     The scheduling policy for the model. If not specified the
    /// @@     default scheduling policy is used for the model. The default
    /// @@     policy is to execute each inference request independently.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Oneof)]
    pub enum SchedulingChoice {
        /// @@    .. cpp:var:: ModelDynamicBatching dynamic_batching
        /// @@
        /// @@       If specified, enables the dynamic-batching scheduling
        /// @@       policy. With dynamic-batching the scheduler may group
        /// @@       together independent requests into a single batch to
        /// @@       improve inference throughput.
        /// @@
        #[prost(message, tag = "11")]
        DynamicBatching(super::ModelDynamicBatching),
        /// @@    .. cpp:var:: ModelSequenceBatching sequence_batching
        /// @@
        /// @@       If specified, enables the sequence-batching scheduling
        /// @@       policy. With sequence-batching, inference requests
        /// @@       with the same correlation ID are routed to the same
        /// @@       model instance. Multiple sequences of inference requests
        /// @@       may be batched together into a single batch to
        /// @@       improve inference throughput.
        /// @@
        #[prost(message, tag = "13")]
        SequenceBatching(super::ModelSequenceBatching),
        /// @@    .. cpp:var:: ModelEnsembling ensemble_scheduling
        /// @@
        /// @@       If specified, enables the model-ensembling scheduling
        /// @@       policy. With model-ensembling, inference requests
        /// @@       will be processed according to the specification, such as an
        /// @@       execution sequence of models. The input specified in this model
        /// @@       config will be the input for the ensemble, and the output
        /// @@       specified will be the output of the ensemble.
        /// @@
        #[prost(message, tag = "15")]
        EnsembleScheduling(super::ModelEnsembling),
    }
}
/// @@
/// @@.. cpp:enum:: DataType
/// @@
/// @@   Data types supported for input and output tensors.
/// @@
#[derive(Clone, Copy, Debug, PartialEq, Eq, Hash, PartialOrd, Ord, ::prost::Enumeration)]
#[repr(i32)]
pub enum DataType {
    /// @@  .. cpp:enumerator:: DataType::INVALID = 0
    TypeInvalid = 0,
    /// @@  .. cpp:enumerator:: DataType::BOOL = 1
    TypeBool = 1,
    /// @@  .. cpp:enumerator:: DataType::UINT8 = 2
    TypeUint8 = 2,
    /// @@  .. cpp:enumerator:: DataType::UINT16 = 3
    TypeUint16 = 3,
    /// @@  .. cpp:enumerator:: DataType::UINT32 = 4
    TypeUint32 = 4,
    /// @@  .. cpp:enumerator:: DataType::UINT64 = 5
    TypeUint64 = 5,
    /// @@  .. cpp:enumerator:: DataType::INT8 = 6
    TypeInt8 = 6,
    /// @@  .. cpp:enumerator:: DataType::INT16 = 7
    TypeInt16 = 7,
    /// @@  .. cpp:enumerator:: DataType::INT32 = 8
    TypeInt32 = 8,
    /// @@  .. cpp:enumerator:: DataType::INT64 = 9
    TypeInt64 = 9,
    /// @@  .. cpp:enumerator:: DataType::FP16 = 10
    TypeFp16 = 10,
    /// @@  .. cpp:enumerator:: DataType::FP32 = 11
    TypeFp32 = 11,
    /// @@  .. cpp:enumerator:: DataType::FP64 = 12
    TypeFp64 = 12,
    /// @@  .. cpp:enumerator:: DataType::STRING = 13
    TypeString = 13,
    /// @@  .. cpp:enumerator:: DataType::BF16 = 14
    TypeBf16 = 14,
}
impl DataType {
    /// String value of the enum field names used in the ProtoBuf definition.
    ///
    /// The values are not transformed in any way and thus are considered stable
    /// (if the ProtoBuf definition does not change) and safe for programmatic use.
    pub fn as_str_name(&self) -> &'static str {
        match self {
            DataType::TypeInvalid => "TYPE_INVALID",
            DataType::TypeBool => "TYPE_BOOL",
            DataType::TypeUint8 => "TYPE_UINT8",
            DataType::TypeUint16 => "TYPE_UINT16",
            DataType::TypeUint32 => "TYPE_UINT32",
            DataType::TypeUint64 => "TYPE_UINT64",
            DataType::TypeInt8 => "TYPE_INT8",
            DataType::TypeInt16 => "TYPE_INT16",
            DataType::TypeInt32 => "TYPE_INT32",
            DataType::TypeInt64 => "TYPE_INT64",
            DataType::TypeFp16 => "TYPE_FP16",
            DataType::TypeFp32 => "TYPE_FP32",
            DataType::TypeFp64 => "TYPE_FP64",
            DataType::TypeString => "TYPE_STRING",
            DataType::TypeBf16 => "TYPE_BF16",
        }
    }
    /// Creates an enum from field names used in the ProtoBuf definition.
    pub fn from_str_name(value: &str) -> ::core::option::Option<Self> {
        match value {
            "TYPE_INVALID" => Some(Self::TypeInvalid),
            "TYPE_BOOL" => Some(Self::TypeBool),
            "TYPE_UINT8" => Some(Self::TypeUint8),
            "TYPE_UINT16" => Some(Self::TypeUint16),
            "TYPE_UINT32" => Some(Self::TypeUint32),
            "TYPE_UINT64" => Some(Self::TypeUint64),
            "TYPE_INT8" => Some(Self::TypeInt8),
            "TYPE_INT16" => Some(Self::TypeInt16),
            "TYPE_INT32" => Some(Self::TypeInt32),
            "TYPE_INT64" => Some(Self::TypeInt64),
            "TYPE_FP16" => Some(Self::TypeFp16),
            "TYPE_FP32" => Some(Self::TypeFp32),
            "TYPE_FP64" => Some(Self::TypeFp64),
            "TYPE_STRING" => Some(Self::TypeString),
            "TYPE_BF16" => Some(Self::TypeBf16),
            _ => None,
        }
    }
}
/// @@
/// @@.. cpp:var:: message ServerLiveRequest
/// @@
/// @@   Request message for ServerLive.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ServerLiveRequest {}
/// @@
/// @@.. cpp:var:: message ServerLiveResponse
/// @@
/// @@   Response message for ServerLive.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ServerLiveResponse {
    /// @@
    /// @@  .. cpp:var:: bool live
    /// @@
    /// @@     True if the inference server is live, false it not live.
    /// @@
    #[prost(bool, tag = "1")]
    pub live: bool,
}
/// @@
/// @@.. cpp:var:: message ServerReadyRequest
/// @@
/// @@   Request message for ServerReady.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ServerReadyRequest {}
/// @@
/// @@.. cpp:var:: message ServerReadyResponse
/// @@
/// @@   Response message for ServerReady.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ServerReadyResponse {
    /// @@
    /// @@  .. cpp:var:: bool ready
    /// @@
    /// @@     True if the inference server is ready, false it not ready.
    /// @@
    #[prost(bool, tag = "1")]
    pub ready: bool,
}
/// @@
/// @@.. cpp:var:: message ModelReadyRequest
/// @@
/// @@   Request message for ModelReady.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelReadyRequest {
    /// @@
    /// @@  .. cpp:var:: string name
    /// @@
    /// @@     The name of the model to check for readiness.
    /// @@
    #[prost(string, tag = "1")]
    pub name: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: string version
    /// @@
    /// @@     The version of the model to check for readiness. If not given the
    /// @@     server will choose a version based on the model and internal policy.
    /// @@
    #[prost(string, tag = "2")]
    pub version: ::prost::alloc::string::String,
}
/// @@
/// @@.. cpp:var:: message ModelReadyResponse
/// @@
/// @@   Response message for ModelReady.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelReadyResponse {
    /// @@
    /// @@  .. cpp:var:: bool ready
    /// @@
    /// @@     True if the model is ready, false it not ready.
    /// @@
    #[prost(bool, tag = "1")]
    pub ready: bool,
}
/// @@
/// @@.. cpp:var:: message ServerMetadataRequest
/// @@
/// @@   Request message for ServerMetadata.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ServerMetadataRequest {}
/// @@
/// @@.. cpp:var:: message ServerMetadataResponse
/// @@
/// @@   Response message for ServerMetadata.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ServerMetadataResponse {
    /// @@
    /// @@  .. cpp:var:: string name
    /// @@
    /// @@     The server name.
    /// @@
    #[prost(string, tag = "1")]
    pub name: ::prost::alloc::string::String,
    /// @@
    /// @@  .. cpp:var:: string version
    /// @@
    /// @@     The server version.
    /// @@
    #[prost(string, tag = "2")]
    pub version: ::prost::alloc::string::String,
    /// @@
    /// @@  .. cpp:var:: string extensions (repeated)
    /// @@
    /// @@     The extensions supported by the server.
    /// @@
    #[prost(string, repeated, tag = "3")]
    pub extensions: ::prost::alloc::vec::Vec<::prost::alloc::string::String>,
}
/// @@
/// @@.. cpp:var:: message ModelMetadataRequest
/// @@
/// @@   Request message for ModelMetadata.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelMetadataRequest {
    /// @@
    /// @@  .. cpp:var:: string name
    /// @@
    /// @@     The name of the model.
    /// @@
    #[prost(string, tag = "1")]
    pub name: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: string version
    /// @@
    /// @@     The version of the model to check for readiness. If not
    /// @@     given the server will choose a version based on the
    /// @@     model and internal policy.
    /// @@
    #[prost(string, tag = "2")]
    pub version: ::prost::alloc::string::String,
}
/// @@
/// @@.. cpp:var:: message ModelMetadataResponse
/// @@
/// @@   Response message for ModelMetadata.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelMetadataResponse {
    /// @@
    /// @@  .. cpp:var:: string name
    /// @@
    /// @@     The model name.
    /// @@
    #[prost(string, tag = "1")]
    pub name: ::prost::alloc::string::String,
    /// @@
    /// @@  .. cpp:var:: string versions (repeated)
    /// @@
    /// @@     The versions of the model.
    /// @@
    #[prost(string, repeated, tag = "2")]
    pub versions: ::prost::alloc::vec::Vec<::prost::alloc::string::String>,
    /// @@
    /// @@  .. cpp:var:: string platform
    /// @@
    /// @@     The model's platform.
    /// @@
    #[prost(string, tag = "3")]
    pub platform: ::prost::alloc::string::String,
    /// @@
    /// @@  .. cpp:var:: TensorMetadata inputs (repeated)
    /// @@
    /// @@     The model's inputs.
    /// @@
    #[prost(message, repeated, tag = "4")]
    pub inputs: ::prost::alloc::vec::Vec<model_metadata_response::TensorMetadata>,
    /// @@
    /// @@  .. cpp:var:: TensorMetadata outputs (repeated)
    /// @@
    /// @@     The model's outputs.
    /// @@
    #[prost(message, repeated, tag = "5")]
    pub outputs: ::prost::alloc::vec::Vec<model_metadata_response::TensorMetadata>,
}
/// Nested message and enum types in `ModelMetadataResponse`.
pub mod model_metadata_response {
    /// @@
    /// @@  .. cpp:var:: message TensorMetadata
    /// @@
    /// @@     Metadata for a tensor.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct TensorMetadata {
        /// @@
        /// @@    .. cpp:var:: string name
        /// @@
        /// @@       The tensor name.
        /// @@
        #[prost(string, tag = "1")]
        pub name: ::prost::alloc::string::String,
        /// @@
        /// @@    .. cpp:var:: string datatype
        /// @@
        /// @@       The tensor data type.
        /// @@
        #[prost(string, tag = "2")]
        pub datatype: ::prost::alloc::string::String,
        /// @@
        /// @@    .. cpp:var:: int64 shape (repeated)
        /// @@
        /// @@       The tensor shape. A variable-size dimension is represented
        /// @@       by a -1 value.
        /// @@
        #[prost(int64, repeated, tag = "3")]
        pub shape: ::prost::alloc::vec::Vec<i64>,
    }
}
/// @@
/// @@.. cpp:var:: message InferParameter
/// @@
/// @@   An inference parameter value.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct InferParameter {
    /// @@  .. cpp:var:: oneof parameter_choice
    /// @@
    /// @@     The parameter value can be a string, an int64 or
    /// @@     a boolean
    /// @@
    #[prost(oneof = "infer_parameter::ParameterChoice", tags = "1, 2, 3")]
    pub parameter_choice: ::core::option::Option<infer_parameter::ParameterChoice>,
}
/// Nested message and enum types in `InferParameter`.
pub mod infer_parameter {
    /// @@  .. cpp:var:: oneof parameter_choice
    /// @@
    /// @@     The parameter value can be a string, an int64 or
    /// @@     a boolean
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Oneof)]
    pub enum ParameterChoice {
        /// @@    .. cpp:var:: bool bool_param
        /// @@
        /// @@       A boolean parameter value.
        /// @@
        #[prost(bool, tag = "1")]
        BoolParam(bool),
        /// @@    .. cpp:var:: int64 int64_param
        /// @@
        /// @@       An int64 parameter value.
        /// @@
        #[prost(int64, tag = "2")]
        Int64Param(i64),
        /// @@    .. cpp:var:: string string_param
        /// @@
        /// @@       A string parameter value.
        /// @@
        #[prost(string, tag = "3")]
        StringParam(::prost::alloc::string::String),
    }
}
/// @@
/// @@.. cpp:var:: message InferTensorContents
/// @@
/// @@   The data contained in a tensor represented by the repeated type
/// @@   that matches the tensor's data type. Protobuf oneof is not used
/// @@   because oneofs cannot contain repeated fields.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct InferTensorContents {
    /// @@
    /// @@  .. cpp:var:: bool bool_contents (repeated)
    /// @@
    /// @@     Representation for BOOL data type. The size must match what is
    /// @@     expected by the tensor's shape. The contents must be the flattened,
    /// @@     one-dimensional, row-major order of the tensor elements.
    /// @@
    #[prost(bool, repeated, tag = "1")]
    pub bool_contents: ::prost::alloc::vec::Vec<bool>,
    /// @@
    /// @@  .. cpp:var:: int32 int_contents (repeated)
    /// @@
    /// @@     Representation for INT8, INT16, and INT32 data types. The size
    /// @@     must match what is expected by the tensor's shape. The contents
    /// @@     must be the flattened, one-dimensional, row-major order of the
    /// @@     tensor elements.
    /// @@
    #[prost(int32, repeated, tag = "2")]
    pub int_contents: ::prost::alloc::vec::Vec<i32>,
    /// @@
    /// @@  .. cpp:var:: int64 int64_contents (repeated)
    /// @@
    /// @@     Representation for INT64 data types. The size must match what
    /// @@     is expected by the tensor's shape. The contents must be the
    /// @@     flattened, one-dimensional, row-major order of the tensor elements.
    /// @@
    #[prost(int64, repeated, tag = "3")]
    pub int64_contents: ::prost::alloc::vec::Vec<i64>,
    /// @@
    /// @@  .. cpp:var:: uint32 uint_contents (repeated)
    /// @@
    /// @@     Representation for UINT8, UINT16, and UINT32 data types. The size
    /// @@     must match what is expected by the tensor's shape. The contents
    /// @@     must be the flattened, one-dimensional, row-major order of the
    /// @@     tensor elements.
    /// @@
    #[prost(uint32, repeated, tag = "4")]
    pub uint_contents: ::prost::alloc::vec::Vec<u32>,
    /// @@
    /// @@  .. cpp:var:: uint64 uint64_contents (repeated)
    /// @@
    /// @@     Representation for UINT64 data types. The size must match what
    /// @@     is expected by the tensor's shape. The contents must be the
    /// @@     flattened, one-dimensional, row-major order of the tensor elements.
    /// @@
    #[prost(uint64, repeated, tag = "5")]
    pub uint64_contents: ::prost::alloc::vec::Vec<u64>,
    /// @@
    /// @@  .. cpp:var:: float fp32_contents (repeated)
    /// @@
    /// @@     Representation for FP32 data type. The size must match what is
    /// @@     expected by the tensor's shape. The contents must be the flattened,
    /// @@     one-dimensional, row-major order of the tensor elements.
    /// @@
    #[prost(float, repeated, tag = "6")]
    pub fp32_contents: ::prost::alloc::vec::Vec<f32>,
    /// @@
    /// @@  .. cpp:var:: double fp64_contents (repeated)
    /// @@
    /// @@     Representation for FP64 data type. The size must match what is
    /// @@     expected by the tensor's shape. The contents must be the flattened,
    /// @@     one-dimensional, row-major order of the tensor elements.
    /// @@
    #[prost(double, repeated, tag = "7")]
    pub fp64_contents: ::prost::alloc::vec::Vec<f64>,
    /// @@
    /// @@  .. cpp:var:: bytes bytes_contents (repeated)
    /// @@
    /// @@     Representation for BYTES data type. The size must match what is
    /// @@     expected by the tensor's shape. The contents must be the flattened,
    /// @@     one-dimensional, row-major order of the tensor elements.
    /// @@
    #[prost(bytes = "vec", repeated, tag = "8")]
    pub bytes_contents: ::prost::alloc::vec::Vec<::prost::alloc::vec::Vec<u8>>,
}
/// @@
/// @@.. cpp:var:: message ModelInferRequest
/// @@
/// @@   Request message for ModelInfer.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelInferRequest {
    /// @@  .. cpp:var:: string model_name
    /// @@
    /// @@     The name of the model to use for inferencing.
    /// @@
    #[prost(string, tag = "1")]
    pub model_name: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: string model_version
    /// @@
    /// @@     The version of the model to use for inference. If not
    /// @@     given the latest/most-recent version of the model is used.
    /// @@
    #[prost(string, tag = "2")]
    pub model_version: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: string id
    /// @@
    /// @@     Optional identifier for the request. If specified will be
    /// @@     returned in the response.
    /// @@
    #[prost(string, tag = "3")]
    pub id: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: map<string,InferParameter> parameters
    /// @@
    /// @@     Optional inference parameters.
    /// @@
    #[prost(map = "string, message", tag = "4")]
    pub parameters: ::std::collections::HashMap<
        ::prost::alloc::string::String,
        InferParameter,
    >,
    /// @@
    /// @@  .. cpp:var:: InferInputTensor inputs (repeated)
    /// @@
    /// @@     The input tensors for the inference.
    /// @@
    #[prost(message, repeated, tag = "5")]
    pub inputs: ::prost::alloc::vec::Vec<model_infer_request::InferInputTensor>,
    /// @@
    /// @@  .. cpp:var:: InferRequestedOutputTensor outputs (repeated)
    /// @@
    /// @@     The requested output tensors for the inference. Optional, if not
    /// @@     specified all outputs specified in the model config will be
    /// @@     returned.
    /// @@
    #[prost(message, repeated, tag = "6")]
    pub outputs: ::prost::alloc::vec::Vec<
        model_infer_request::InferRequestedOutputTensor,
    >,
    /// @@
    /// @@  .. cpp:var:: bytes raw_input_contents
    /// @@
    /// @@     The data contained in an input tensor can be represented in
    /// @@     "raw" bytes form or in the repeated type that matches the
    /// @@     tensor's data type. Using the "raw" bytes form will
    /// @@     typically allow higher performance due to the way protobuf
    /// @@     allocation and reuse interacts with GRPC. For example, see
    /// @@     <https://github.com/grpc/grpc/issues/23231.>
    /// @@
    /// @@     To use the raw representation 'raw_input_contents' must be
    /// @@     initialized with data for each tensor in the same order as
    /// @@     'inputs'. For each tensor, the size of this content must
    /// @@     match what is expected by the tensor's shape and data
    /// @@     type. The raw data must be the flattened, one-dimensional,
    /// @@     row-major order of the tensor elements without any stride
    /// @@     or padding between the elements. Note that the FP16 and BF16 data
    /// @@     types must be represented as raw content as there is no
    /// @@     specific data type for a 16-bit float type.
    /// @@
    /// @@     If this field is specified then InferInputTensor::contents
    /// @@     must not be specified for any input tensor.
    /// @@
    #[prost(bytes = "vec", repeated, tag = "7")]
    pub raw_input_contents: ::prost::alloc::vec::Vec<::prost::alloc::vec::Vec<u8>>,
}
/// Nested message and enum types in `ModelInferRequest`.
pub mod model_infer_request {
    /// @@
    /// @@  .. cpp:var:: message InferInputTensor
    /// @@
    /// @@     An input tensor for an inference request.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct InferInputTensor {
        /// @@
        /// @@    .. cpp:var:: string name
        /// @@
        /// @@       The tensor name.
        /// @@
        #[prost(string, tag = "1")]
        pub name: ::prost::alloc::string::String,
        /// @@
        /// @@    .. cpp:var:: string datatype
        /// @@
        /// @@       The tensor data type.
        /// @@
        #[prost(string, tag = "2")]
        pub datatype: ::prost::alloc::string::String,
        /// @@
        /// @@    .. cpp:var:: int64 shape (repeated)
        /// @@
        /// @@       The tensor shape.
        /// @@
        #[prost(int64, repeated, tag = "3")]
        pub shape: ::prost::alloc::vec::Vec<i64>,
        /// @@    .. cpp:var:: map<string,InferParameter> parameters
        /// @@
        /// @@       Optional inference input tensor parameters.
        /// @@
        #[prost(map = "string, message", tag = "4")]
        pub parameters: ::std::collections::HashMap<
            ::prost::alloc::string::String,
            super::InferParameter,
        >,
        /// @@    .. cpp:var:: InferTensorContents contents
        /// @@
        /// @@       The tensor contents using a data-type format. This field
        /// @@       must not be specified if tensor contents are being specified
        /// @@       in ModelInferRequest.raw_input_contents.
        /// @@
        #[prost(message, optional, tag = "5")]
        pub contents: ::core::option::Option<super::InferTensorContents>,
    }
    /// @@
    /// @@  .. cpp:var:: message InferRequestedOutputTensor
    /// @@
    /// @@     An output tensor requested for an inference request.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct InferRequestedOutputTensor {
        /// @@
        /// @@    .. cpp:var:: string name
        /// @@
        /// @@       The tensor name.
        /// @@
        #[prost(string, tag = "1")]
        pub name: ::prost::alloc::string::String,
        /// @@    .. cpp:var:: map<string,InferParameter> parameters
        /// @@
        /// @@       Optional requested output tensor parameters.
        /// @@
        #[prost(map = "string, message", tag = "2")]
        pub parameters: ::std::collections::HashMap<
            ::prost::alloc::string::String,
            super::InferParameter,
        >,
    }
}
/// @@
/// @@.. cpp:var:: message ModelInferResponse
/// @@
/// @@   Response message for ModelInfer.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelInferResponse {
    /// @@  .. cpp:var:: string model_name
    /// @@
    /// @@     The name of the model used for inference.
    /// @@
    #[prost(string, tag = "1")]
    pub model_name: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: string model_version
    /// @@
    /// @@     The version of the model used for inference.
    /// @@
    #[prost(string, tag = "2")]
    pub model_version: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: string id
    /// @@
    /// @@     The id of the inference request if one was specified.
    /// @@
    #[prost(string, tag = "3")]
    pub id: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: map<string,InferParameter> parameters
    /// @@
    /// @@     Optional inference response parameters.
    /// @@
    #[prost(map = "string, message", tag = "4")]
    pub parameters: ::std::collections::HashMap<
        ::prost::alloc::string::String,
        InferParameter,
    >,
    /// @@
    /// @@  .. cpp:var:: InferOutputTensor outputs (repeated)
    /// @@
    /// @@     The output tensors holding inference results.
    /// @@
    #[prost(message, repeated, tag = "5")]
    pub outputs: ::prost::alloc::vec::Vec<model_infer_response::InferOutputTensor>,
    /// @@
    /// @@  .. cpp:var:: bytes raw_output_contents
    /// @@
    /// @@     The data contained in an output tensor can be represented in
    /// @@     "raw" bytes form or in the repeated type that matches the
    /// @@     tensor's data type. Using the "raw" bytes form will
    /// @@     typically allow higher performance due to the way protobuf
    /// @@     allocation and reuse interacts with GRPC. For example, see
    /// @@     <https://github.com/grpc/grpc/issues/23231.>
    /// @@
    /// @@     To use the raw representation 'raw_output_contents' must be
    /// @@     initialized with data for each tensor in the same order as
    /// @@     'outputs'. For each tensor, the size of this content must
    /// @@     match what is expected by the tensor's shape and data
    /// @@     type. The raw data must be the flattened, one-dimensional,
    /// @@     row-major order of the tensor elements without any stride
    /// @@     or padding between the elements. Note that the FP16 and BF16 data
    /// @@     types must be represented as raw content as there is no
    /// @@     specific data type for a 16-bit float type.
    /// @@
    /// @@     If this field is specified then InferOutputTensor::contents
    /// @@     must not be specified for any output tensor.
    /// @@
    #[prost(bytes = "vec", repeated, tag = "6")]
    pub raw_output_contents: ::prost::alloc::vec::Vec<::prost::alloc::vec::Vec<u8>>,
}
/// Nested message and enum types in `ModelInferResponse`.
pub mod model_infer_response {
    /// @@
    /// @@  .. cpp:var:: message InferOutputTensor
    /// @@
    /// @@     An output tensor returned for an inference request.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct InferOutputTensor {
        /// @@
        /// @@    .. cpp:var:: string name
        /// @@
        /// @@       The tensor name.
        /// @@
        #[prost(string, tag = "1")]
        pub name: ::prost::alloc::string::String,
        /// @@
        /// @@    .. cpp:var:: string datatype
        /// @@
        /// @@       The tensor data type.
        /// @@
        #[prost(string, tag = "2")]
        pub datatype: ::prost::alloc::string::String,
        /// @@
        /// @@    .. cpp:var:: int64 shape (repeated)
        /// @@
        /// @@       The tensor shape.
        /// @@
        #[prost(int64, repeated, tag = "3")]
        pub shape: ::prost::alloc::vec::Vec<i64>,
        /// @@    .. cpp:var:: map<string,InferParameter> parameters
        /// @@
        /// @@       Optional output tensor parameters.
        /// @@
        #[prost(map = "string, message", tag = "4")]
        pub parameters: ::std::collections::HashMap<
            ::prost::alloc::string::String,
            super::InferParameter,
        >,
        /// @@    .. cpp:var:: InferTensorContents contents
        /// @@
        /// @@       The tensor contents using a data-type format. This field
        /// @@       must not be specified if tensor contents are being specified
        /// @@       in ModelInferResponse.raw_output_contents.
        /// @@
        #[prost(message, optional, tag = "5")]
        pub contents: ::core::option::Option<super::InferTensorContents>,
    }
}
/// @@
/// @@.. cpp:var:: message ModelStreamInferResponse
/// @@
/// @@   Response message for ModelStreamInfer.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelStreamInferResponse {
    /// @@
    /// @@  .. cpp:var:: string error_message
    /// @@
    /// @@     The message describing the error. The empty message
    /// @@     indicates the inference was successful without errors.
    /// @@
    #[prost(string, tag = "1")]
    pub error_message: ::prost::alloc::string::String,
    /// @@
    /// @@  .. cpp:var:: ModelInferResponse infer_response
    /// @@
    /// @@     Holds the results of the request.
    /// @@
    #[prost(message, optional, tag = "2")]
    pub infer_response: ::core::option::Option<ModelInferResponse>,
}
/// @@
/// @@.. cpp:var:: message ModelConfigRequest
/// @@
/// @@   Request message for ModelConfig.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelConfigRequest {
    /// @@
    /// @@  .. cpp:var:: string name
    /// @@
    /// @@     The name of the model.
    /// @@
    #[prost(string, tag = "1")]
    pub name: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: string version
    /// @@
    /// @@     The version of the model. If not given the model version
    /// @@     is selected automatically based on the version policy.
    /// @@
    #[prost(string, tag = "2")]
    pub version: ::prost::alloc::string::String,
}
/// @@
/// @@.. cpp:var:: message ModelConfigResponse
/// @@
/// @@   Response message for ModelConfig.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelConfigResponse {
    /// @@
    /// @@  .. cpp:var:: ModelConfig config
    /// @@
    /// @@     The model configuration.
    /// @@
    #[prost(message, optional, tag = "1")]
    pub config: ::core::option::Option<ModelConfig>,
}
/// @@
/// @@.. cpp:var:: message ModelStatisticsRequest
/// @@
/// @@   Request message for ModelStatistics.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelStatisticsRequest {
    /// @@  .. cpp:var:: string name
    /// @@
    /// @@     The name of the model. If not given returns statistics for
    /// @@     all models.
    /// @@
    #[prost(string, tag = "1")]
    pub name: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: string version
    /// @@
    /// @@     The version of the model. If not given returns statistics for
    /// @@     all model versions.
    /// @@
    #[prost(string, tag = "2")]
    pub version: ::prost::alloc::string::String,
}
/// @@
/// @@.. cpp:var:: message StatisticDuration
/// @@
/// @@   Statistic recording a cumulative duration metric.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct StatisticDuration {
    /// @@  .. cpp:var:: uint64 count
    /// @@
    /// @@     Cumulative number of times this metric occurred.
    /// @@
    #[prost(uint64, tag = "1")]
    pub count: u64,
    /// @@  .. cpp:var:: uint64 total_time_ns
    /// @@
    /// @@     Total collected duration of this metric in nanoseconds.
    /// @@
    #[prost(uint64, tag = "2")]
    pub ns: u64,
}
/// @@
/// @@.. cpp:var:: message InferStatistics
/// @@
/// @@   Inference statistics.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct InferStatistics {
    /// @@  .. cpp:var:: StatisticDuration success
    /// @@
    /// @@     Cumulative count and duration for successful inference
    /// @@     request. The "success" count and cumulative duration includes
    /// @@     cache hits.
    /// @@
    #[prost(message, optional, tag = "1")]
    pub success: ::core::option::Option<StatisticDuration>,
    /// @@  .. cpp:var:: StatisticDuration fail
    /// @@
    /// @@     Cumulative count and duration for failed inference
    /// @@     request.
    /// @@
    #[prost(message, optional, tag = "2")]
    pub fail: ::core::option::Option<StatisticDuration>,
    /// @@  .. cpp:var:: StatisticDuration queue
    /// @@
    /// @@     The count and cumulative duration that inference requests wait in
    /// @@     scheduling or other queues. The "queue" count and cumulative
    /// @@     duration includes cache hits.
    /// @@
    #[prost(message, optional, tag = "3")]
    pub queue: ::core::option::Option<StatisticDuration>,
    /// @@  .. cpp:var:: StatisticDuration compute_input
    /// @@
    /// @@     The count and cumulative duration to prepare input tensor data as
    /// @@     required by the model framework / backend. For example, this duration
    /// @@     should include the time to copy input tensor data to the GPU.
    /// @@     The "compute_input" count and cumulative duration do not account for
    /// @@     requests that were a cache hit. See the "cache_hit" field for more
    /// @@     info.
    /// @@
    #[prost(message, optional, tag = "4")]
    pub compute_input: ::core::option::Option<StatisticDuration>,
    /// @@  .. cpp:var:: StatisticDuration compute_infer
    /// @@
    /// @@     The count and cumulative duration to execute the model.
    /// @@     The "compute_infer" count and cumulative duration do not account for
    /// @@     requests that were a cache hit. See the "cache_hit" field for more
    /// @@     info.
    /// @@
    #[prost(message, optional, tag = "5")]
    pub compute_infer: ::core::option::Option<StatisticDuration>,
    /// @@  .. cpp:var:: StatisticDuration compute_output
    /// @@
    /// @@     The count and cumulative duration to extract output tensor data
    /// @@     produced by the model framework / backend. For example, this duration
    /// @@     should include the time to copy output tensor data from the GPU.
    /// @@     The "compute_output" count and cumulative duration do not account for
    /// @@     requests that were a cache hit. See the "cache_hit" field for more
    /// @@     info.
    /// @@
    #[prost(message, optional, tag = "6")]
    pub compute_output: ::core::option::Option<StatisticDuration>,
    /// @@  .. cpp:var:: StatisticDuration cache_hit
    /// @@
    /// @@     The count of response cache hits and cumulative duration to lookup
    /// @@     and extract output tensor data from the Response Cache on a cache
    /// @@     hit. For example, this duration should include the time to copy
    /// @@     output tensor data from the Response Cache to the response object.
    /// @@     On cache hits, triton does not need to go to the model/backend
    /// @@     for the output tensor data, so the "compute_input", "compute_infer",
    /// @@     and "compute_output" fields are not updated. Assuming the response
    /// @@     cache is enabled for a given model, a cache hit occurs for a
    /// @@     request to that model when the request metadata (model name,
    /// @@     model version, model inputs) hashes to an existing entry in the
    /// @@     cache. On a cache miss, the request hash and response output tensor
    /// @@     data is added to the cache. See response cache docs for more info:
    /// @@     <https://github.com/triton-inference-server/server/blob/main/docs/response_cache.md>
    /// @@
    #[prost(message, optional, tag = "7")]
    pub cache_hit: ::core::option::Option<StatisticDuration>,
    /// @@  .. cpp:var:: StatisticDuration cache_miss
    /// @@
    /// @@     The count of response cache misses and cumulative duration to lookup
    /// @@     and insert output tensor data from the computed response to the cache.
    /// @@     For example, this duration should include the time to copy
    /// @@     output tensor data from the response object to the Response Cache.
    /// @@     Assuming the response cache is enabled for a given model, a cache
    /// @@     miss occurs for a request to that model when the request metadata
    /// @@     does NOT hash to an existing entry in the cache. See the response
    /// @@     cache docs for more info:
    /// @@     <https://github.com/triton-inference-server/server/blob/main/docs/response_cache.md>
    /// @@
    #[prost(message, optional, tag = "8")]
    pub cache_miss: ::core::option::Option<StatisticDuration>,
}
/// @@
/// @@.. cpp:var:: message InferBatchStatistics
/// @@
/// @@   Inference batch statistics.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct InferBatchStatistics {
    /// @@  .. cpp:var:: uint64 batch_size
    /// @@
    /// @@     The size of the batch.
    /// @@
    #[prost(uint64, tag = "1")]
    pub batch_size: u64,
    /// @@  .. cpp:var:: StatisticDuration compute_input
    /// @@
    /// @@     The count and cumulative duration to prepare input tensor data as
    /// @@     required by the model framework / backend with the given batch size.
    /// @@     For example, this duration should include the time to copy input
    /// @@     tensor data to the GPU.
    /// @@
    #[prost(message, optional, tag = "2")]
    pub compute_input: ::core::option::Option<StatisticDuration>,
    /// @@  .. cpp:var:: StatisticDuration compute_infer
    /// @@
    /// @@     The count and cumulative duration to execute the model with the given
    /// @@     batch size.
    /// @@
    #[prost(message, optional, tag = "3")]
    pub compute_infer: ::core::option::Option<StatisticDuration>,
    /// @@  .. cpp:var:: StatisticDuration compute_output
    /// @@
    /// @@     The count and cumulative duration to extract output tensor data
    /// @@     produced by the model framework / backend with the given batch size.
    /// @@     For example, this duration should include the time to copy output
    /// @@     tensor data from the GPU.
    /// @@
    #[prost(message, optional, tag = "4")]
    pub compute_output: ::core::option::Option<StatisticDuration>,
}
/// @@
/// @@.. cpp:var:: message ModelStatistics
/// @@
/// @@   Statistics for a specific model and version.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelStatistics {
    /// @@  .. cpp:var:: string name
    /// @@
    /// @@     The name of the model. If not given returns statistics for all
    /// @@
    #[prost(string, tag = "1")]
    pub name: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: string version
    /// @@
    /// @@     The version of the model.
    /// @@
    #[prost(string, tag = "2")]
    pub version: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: uint64 last_inference
    /// @@
    /// @@     The timestamp of the last inference request made for this model,
    /// @@     as milliseconds since the epoch.
    /// @@
    #[prost(uint64, tag = "3")]
    pub last_inference: u64,
    /// @@  .. cpp:var:: uint64 last_inference
    /// @@
    /// @@     The cumulative count of successful inference requests made for this
    /// @@     model. Each inference in a batched request is counted as an
    /// @@     individual inference. For example, if a client sends a single
    /// @@     inference request with batch size 64, "inference_count" will be
    /// @@     incremented by 64. Similarly, if a clients sends 64 individual
    /// @@     requests each with batch size 1, "inference_count" will be
    /// @@     incremented by 64. The "inference_count" value DOES NOT include
    /// @@     cache hits.
    /// @@
    #[prost(uint64, tag = "4")]
    pub inference_count: u64,
    /// @@  .. cpp:var:: uint64 last_inference
    /// @@
    /// @@     The cumulative count of the number of successful inference executions
    /// @@     performed for the model. When dynamic batching is enabled, a single
    /// @@     model execution can perform inferencing for more than one inference
    /// @@     request. For example, if a clients sends 64 individual requests each
    /// @@     with batch size 1 and the dynamic batcher batches them into a single
    /// @@     large batch for model execution then "execution_count" will be
    /// @@     incremented by 1. If, on the other hand, the dynamic batcher is not
    /// @@     enabled for that each of the 64 individual requests is executed
    /// @@     independently, then "execution_count" will be incremented by 64.
    /// @@     The "execution_count" value DOES NOT include cache hits.
    /// @@
    #[prost(uint64, tag = "5")]
    pub execution_count: u64,
    /// @@  .. cpp:var:: InferStatistics inference_stats
    /// @@
    /// @@     The aggregate statistics for the model/version.
    /// @@
    #[prost(message, optional, tag = "6")]
    pub inference_stats: ::core::option::Option<InferStatistics>,
    /// @@  .. cpp:var:: InferBatchStatistics batch_stats (repeated)
    /// @@
    /// @@     The aggregate statistics for each different batch size that is
    /// @@     executed in the model. The batch statistics indicate how many actual
    /// @@     model executions were performed and show differences due to different
    /// @@     batch size (for example, larger batches typically take longer to
    /// @@     compute).
    /// @@
    #[prost(message, repeated, tag = "7")]
    pub batch_stats: ::prost::alloc::vec::Vec<InferBatchStatistics>,
}
/// @@
/// @@.. cpp:var:: message ModelStatisticsResponse
/// @@
/// @@   Response message for ModelStatistics.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelStatisticsResponse {
    /// @@  .. cpp:var:: ModelStatistics model_stats (repeated)
    /// @@
    /// @@     Statistics for each requested model.
    /// @@
    #[prost(message, repeated, tag = "1")]
    pub model_stats: ::prost::alloc::vec::Vec<ModelStatistics>,
}
/// @@
/// @@.. cpp:var:: message ModelRepositoryParameter
/// @@
/// @@   An model repository parameter value.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ModelRepositoryParameter {
    /// @@  .. cpp:var:: oneof parameter_choice
    /// @@
    /// @@     The parameter value can be a string, an int64 or
    /// @@     a boolean
    /// @@
    #[prost(oneof = "model_repository_parameter::ParameterChoice", tags = "1, 2, 3, 4")]
    pub parameter_choice: ::core::option::Option<
        model_repository_parameter::ParameterChoice,
    >,
}
/// Nested message and enum types in `ModelRepositoryParameter`.
pub mod model_repository_parameter {
    /// @@  .. cpp:var:: oneof parameter_choice
    /// @@
    /// @@     The parameter value can be a string, an int64 or
    /// @@     a boolean
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Oneof)]
    pub enum ParameterChoice {
        /// @@    .. cpp:var:: bool bool_param
        /// @@
        /// @@       A boolean parameter value.
        /// @@
        #[prost(bool, tag = "1")]
        BoolParam(bool),
        /// @@    .. cpp:var:: int64 int64_param
        /// @@
        /// @@       An int64 parameter value.
        /// @@
        #[prost(int64, tag = "2")]
        Int64Param(i64),
        /// @@    .. cpp:var:: string string_param
        /// @@
        /// @@       A string parameter value.
        /// @@
        #[prost(string, tag = "3")]
        StringParam(::prost::alloc::string::String),
        /// @@    .. cpp:var:: bytes bytes_param
        /// @@
        /// @@       A bytes parameter value.
        /// @@
        #[prost(bytes, tag = "4")]
        BytesParam(::prost::alloc::vec::Vec<u8>),
    }
}
/// @@
/// @@.. cpp:var:: message RepositoryIndexRequest
/// @@
/// @@   Request message for RepositoryIndex.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct RepositoryIndexRequest {
    /// @@  .. cpp:var:: string repository_name
    /// @@
    /// @@     The name of the repository. If empty the index is returned
    /// @@     for all repositories.
    /// @@
    #[prost(string, tag = "1")]
    pub repository_name: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: bool ready
    /// @@
    /// @@     If true returned only models currently ready for inferencing.
    /// @@
    #[prost(bool, tag = "2")]
    pub ready: bool,
}
/// @@
/// @@.. cpp:var:: message RepositoryIndexResponse
/// @@
/// @@   Response message for RepositoryIndex.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct RepositoryIndexResponse {
    /// @@
    /// @@  .. cpp:var:: ModelIndex models (repeated)
    /// @@
    /// @@     An index entry for each model.
    /// @@
    #[prost(message, repeated, tag = "1")]
    pub models: ::prost::alloc::vec::Vec<repository_index_response::ModelIndex>,
}
/// Nested message and enum types in `RepositoryIndexResponse`.
pub mod repository_index_response {
    /// @@
    /// @@  .. cpp:var:: message ModelIndex
    /// @@
    /// @@     Index entry for a model.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct ModelIndex {
        /// @@
        /// @@    .. cpp:var:: string name
        /// @@
        /// @@       The name of the model.
        /// @@
        #[prost(string, tag = "1")]
        pub name: ::prost::alloc::string::String,
        /// @@    .. cpp:var:: string version
        /// @@
        /// @@       The version of the model.
        /// @@
        #[prost(string, tag = "2")]
        pub version: ::prost::alloc::string::String,
        /// @@
        /// @@    .. cpp:var:: string state
        /// @@
        /// @@       The state of the model.
        /// @@
        #[prost(string, tag = "3")]
        pub state: ::prost::alloc::string::String,
        /// @@
        /// @@    .. cpp:var:: string reason
        /// @@
        /// @@       The reason, if any, that the model is in the given state.
        /// @@
        #[prost(string, tag = "4")]
        pub reason: ::prost::alloc::string::String,
    }
}
/// @@
/// @@.. cpp:var:: message RepositoryModelLoadRequest
/// @@
/// @@   Request message for RepositoryModelLoad.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct RepositoryModelLoadRequest {
    /// @@  .. cpp:var:: string repository_name
    /// @@
    /// @@     The name of the repository to load from. If empty the model
    /// @@     is loaded from any repository.
    /// @@
    #[prost(string, tag = "1")]
    pub repository_name: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: string repository_name
    /// @@
    /// @@     The name of the model to load, or reload.
    /// @@
    #[prost(string, tag = "2")]
    pub model_name: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: map<string,ModelRepositoryParameter> parameters
    /// @@
    /// @@     Optional model repository request parameters.
    /// @@
    #[prost(map = "string, message", tag = "3")]
    pub parameters: ::std::collections::HashMap<
        ::prost::alloc::string::String,
        ModelRepositoryParameter,
    >,
}
/// @@
/// @@.. cpp:var:: message RepositoryModelLoadResponse
/// @@
/// @@   Response message for RepositoryModelLoad.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct RepositoryModelLoadResponse {}
/// @@
/// @@.. cpp:var:: message RepositoryModelUnloadRequest
/// @@
/// @@   Request message for RepositoryModelUnload.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct RepositoryModelUnloadRequest {
    /// @@  .. cpp:var:: string repository_name
    /// @@
    /// @@     The name of the repository from which the model was originally
    /// @@     loaded. If empty the repository is not considered.
    /// @@
    #[prost(string, tag = "1")]
    pub repository_name: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: string repository_name
    /// @@
    /// @@     The name of the model to unload.
    /// @@
    #[prost(string, tag = "2")]
    pub model_name: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: map<string,ModelRepositoryParameter> parameters
    /// @@
    /// @@     Optional model repository request parameters.
    /// @@
    #[prost(map = "string, message", tag = "3")]
    pub parameters: ::std::collections::HashMap<
        ::prost::alloc::string::String,
        ModelRepositoryParameter,
    >,
}
/// @@
/// @@.. cpp:var:: message RepositoryModelUnloadResponse
/// @@
/// @@   Response message for RepositoryModelUnload.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct RepositoryModelUnloadResponse {}
/// @@
/// @@.. cpp:var:: message SystemSharedMemoryStatusRequest
/// @@
/// @@   Request message for SystemSharedMemoryStatus.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct SystemSharedMemoryStatusRequest {
    /// @@
    /// @@  .. cpp:var:: string name
    /// @@
    /// @@     The name of the region to get status for. If empty the
    /// @@     status is returned for all registered regions.
    /// @@
    #[prost(string, tag = "1")]
    pub name: ::prost::alloc::string::String,
}
/// @@
/// @@.. cpp:var:: message SystemSharedMemoryStatusResponse
/// @@
/// @@   Response message for SystemSharedMemoryStatus.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct SystemSharedMemoryStatusResponse {
    /// @@
    /// @@  .. cpp:var:: map<string,RegionStatus> regions
    /// @@
    /// @@     Status for each of the registered regions, indexed by
    /// @@     region name.
    /// @@
    #[prost(map = "string, message", tag = "1")]
    pub regions: ::std::collections::HashMap<
        ::prost::alloc::string::String,
        system_shared_memory_status_response::RegionStatus,
    >,
}
/// Nested message and enum types in `SystemSharedMemoryStatusResponse`.
pub mod system_shared_memory_status_response {
    /// @@
    /// @@  .. cpp:var:: message RegionStatus
    /// @@
    /// @@     Status for a shared memory region.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct RegionStatus {
        /// @@
        /// @@    .. cpp:var:: string name
        /// @@
        /// @@       The name for the shared memory region.
        /// @@
        #[prost(string, tag = "1")]
        pub name: ::prost::alloc::string::String,
        /// @@    .. cpp:var:: string shared_memory_key
        /// @@
        /// @@       The key of the underlying memory object that contains the
        /// @@       shared memory region.
        /// @@
        #[prost(string, tag = "2")]
        pub key: ::prost::alloc::string::String,
        /// @@    .. cpp:var:: uint64 offset
        /// @@
        /// @@       Offset, in bytes, within the underlying memory object to
        /// @@       the start of the shared memory region.
        /// @@
        #[prost(uint64, tag = "3")]
        pub offset: u64,
        /// @@    .. cpp:var:: uint64 byte_size
        /// @@
        /// @@       Size of the shared memory region, in bytes.
        /// @@
        #[prost(uint64, tag = "4")]
        pub byte_size: u64,
    }
}
/// @@
/// @@.. cpp:var:: message SystemSharedMemoryRegisterRequest
/// @@
/// @@   Request message for SystemSharedMemoryRegister.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct SystemSharedMemoryRegisterRequest {
    /// @@
    /// @@  .. cpp:var:: string name
    /// @@
    /// @@     The name of the region to register.
    /// @@
    #[prost(string, tag = "1")]
    pub name: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: string shared_memory_key
    /// @@
    /// @@     The key of the underlying memory object that contains the
    /// @@     shared memory region.
    /// @@
    #[prost(string, tag = "2")]
    pub key: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: uint64 offset
    /// @@
    /// @@     Offset, in bytes, within the underlying memory object to
    /// @@     the start of the shared memory region.
    /// @@
    #[prost(uint64, tag = "3")]
    pub offset: u64,
    /// @@  .. cpp:var:: uint64 byte_size
    /// @@
    /// @@     Size of the shared memory region, in bytes.
    /// @@
    #[prost(uint64, tag = "4")]
    pub byte_size: u64,
}
/// @@
/// @@.. cpp:var:: message SystemSharedMemoryRegisterResponse
/// @@
/// @@   Response message for SystemSharedMemoryRegister.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct SystemSharedMemoryRegisterResponse {}
/// @@
/// @@.. cpp:var:: message SystemSharedMemoryUnregisterRequest
/// @@
/// @@   Request message for SystemSharedMemoryUnregister.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct SystemSharedMemoryUnregisterRequest {
    /// @@
    /// @@  .. cpp:var:: string name
    /// @@
    /// @@     The name of the system region to unregister. If empty
    /// @@     all system shared-memory regions are unregistered.
    /// @@
    #[prost(string, tag = "1")]
    pub name: ::prost::alloc::string::String,
}
/// @@
/// @@.. cpp:var:: message SystemSharedMemoryUnregisterResponse
/// @@
/// @@   Response message for SystemSharedMemoryUnregister.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct SystemSharedMemoryUnregisterResponse {}
/// @@
/// @@.. cpp:var:: message CudaSharedMemoryStatusRequest
/// @@
/// @@   Request message for CudaSharedMemoryStatus.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct CudaSharedMemoryStatusRequest {
    /// @@
    /// @@  .. cpp:var:: string name
    /// @@
    /// @@     The name of the region to get status for. If empty the
    /// @@     status is returned for all registered regions.
    /// @@
    #[prost(string, tag = "1")]
    pub name: ::prost::alloc::string::String,
}
/// @@
/// @@.. cpp:var:: message CudaSharedMemoryStatusResponse
/// @@
/// @@   Response message for CudaSharedMemoryStatus.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct CudaSharedMemoryStatusResponse {
    /// @@
    /// @@  .. cpp:var:: map<string,RegionStatus> regions
    /// @@
    /// @@     Status for each of the registered regions, indexed by
    /// @@     region name.
    /// @@
    #[prost(map = "string, message", tag = "1")]
    pub regions: ::std::collections::HashMap<
        ::prost::alloc::string::String,
        cuda_shared_memory_status_response::RegionStatus,
    >,
}
/// Nested message and enum types in `CudaSharedMemoryStatusResponse`.
pub mod cuda_shared_memory_status_response {
    /// @@
    /// @@  .. cpp:var:: message RegionStatus
    /// @@
    /// @@     Status for a shared memory region.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct RegionStatus {
        /// @@
        /// @@    .. cpp:var:: string name
        /// @@
        /// @@       The name for the shared memory region.
        /// @@
        #[prost(string, tag = "1")]
        pub name: ::prost::alloc::string::String,
        /// @@    .. cpp:var:: uin64 device_id
        /// @@
        /// @@       The GPU device ID where the cudaIPC handle was created.
        /// @@
        #[prost(uint64, tag = "2")]
        pub device_id: u64,
        /// @@    .. cpp:var:: uint64 byte_size
        /// @@
        /// @@       Size of the shared memory region, in bytes.
        /// @@
        #[prost(uint64, tag = "3")]
        pub byte_size: u64,
    }
}
/// @@
/// @@.. cpp:var:: message CudaSharedMemoryRegisterRequest
/// @@
/// @@   Request message for CudaSharedMemoryRegister.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct CudaSharedMemoryRegisterRequest {
    /// @@
    /// @@  .. cpp:var:: string name
    /// @@
    /// @@     The name of the region to register.
    /// @@
    #[prost(string, tag = "1")]
    pub name: ::prost::alloc::string::String,
    /// @@  .. cpp:var:: bytes raw_handle
    /// @@
    /// @@     The raw serialized cudaIPC handle.
    /// @@
    #[prost(bytes = "vec", tag = "2")]
    pub raw_handle: ::prost::alloc::vec::Vec<u8>,
    /// @@  .. cpp:var:: int64 device_id
    /// @@
    /// @@     The GPU device ID on which the cudaIPC handle was created.
    /// @@
    #[prost(int64, tag = "3")]
    pub device_id: i64,
    /// @@  .. cpp:var:: uint64 byte_size
    /// @@
    /// @@     Size of the shared memory block, in bytes.
    /// @@
    #[prost(uint64, tag = "4")]
    pub byte_size: u64,
}
/// @@
/// @@.. cpp:var:: message CudaSharedMemoryRegisterResponse
/// @@
/// @@   Response message for CudaSharedMemoryRegister.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct CudaSharedMemoryRegisterResponse {}
/// @@
/// @@.. cpp:var:: message CudaSharedMemoryUnregisterRequest
/// @@
/// @@   Request message for CudaSharedMemoryUnregister.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct CudaSharedMemoryUnregisterRequest {
    /// @@
    /// @@  .. cpp:var:: string name
    /// @@
    /// @@     The name of the cuda region to unregister. If empty
    /// @@     all cuda shared-memory regions are unregistered.
    /// @@
    #[prost(string, tag = "1")]
    pub name: ::prost::alloc::string::String,
}
/// @@
/// @@.. cpp:var:: message CudaSharedMemoryUnregisterResponse
/// @@
/// @@   Response message for CudaSharedMemoryUnregister.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct CudaSharedMemoryUnregisterResponse {}
/// @@
/// @@.. cpp:var:: message TraceSettingRequest
/// @@
/// @@   Request message for TraceSetting.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct TraceSettingRequest {
    /// @@  .. cpp:var:: map<string,SettingValue> settings
    /// @@
    /// @@     The new setting values to be updated,
    /// @@     settings that are not specified will remain unchanged.
    /// @@
    #[prost(map = "string, message", tag = "1")]
    pub settings: ::std::collections::HashMap<
        ::prost::alloc::string::String,
        trace_setting_request::SettingValue,
    >,
    /// @@
    /// @@  .. cpp:var:: string model_name
    /// @@
    /// @@     The name of the model to apply the new trace settings.
    /// @@     If not given, the new settings will be applied globally.
    /// @@
    #[prost(string, tag = "2")]
    pub model_name: ::prost::alloc::string::String,
}
/// Nested message and enum types in `TraceSettingRequest`.
pub mod trace_setting_request {
    /// @@
    /// @@  .. cpp:var:: message SettingValue
    /// @@
    /// @@     The values to be associated with a trace setting.
    /// @@     If no value is provided, the setting will be clear and
    /// @@     the global setting value will be used.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct SettingValue {
        /// @@
        /// @@    .. cpp:var:: string value (repeated)
        /// @@
        /// @@       The value.
        /// @@
        #[prost(string, repeated, tag = "1")]
        pub value: ::prost::alloc::vec::Vec<::prost::alloc::string::String>,
    }
}
/// @@
/// @@.. cpp:var:: message TraceSettingResponse
/// @@
/// @@   Response message for TraceSetting.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct TraceSettingResponse {
    /// @@  .. cpp:var:: map<string,SettingValue> settings
    /// @@
    /// @@     The current trace settings, including any changes specified
    /// @@     by TraceSettingRequest.
    /// @@
    #[prost(map = "string, message", tag = "1")]
    pub settings: ::std::collections::HashMap<
        ::prost::alloc::string::String,
        trace_setting_response::SettingValue,
    >,
}
/// Nested message and enum types in `TraceSettingResponse`.
pub mod trace_setting_response {
    /// @@
    /// @@  .. cpp:var:: message SettingValue
    /// @@
    /// @@     The values to be associated with a trace setting.
    /// @@
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct SettingValue {
        /// @@
        /// @@    .. cpp:var:: string value (repeated)
        /// @@
        /// @@       The value.
        /// @@
        #[prost(string, repeated, tag = "1")]
        pub value: ::prost::alloc::vec::Vec<::prost::alloc::string::String>,
    }
}
/// @@
/// @@.. cpp:var:: message LogSettingsRequest
/// @@
/// @@   Request message for LogSettings.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct LogSettingsRequest {
    /// @@  .. cpp:var:: map<string,SettingValue> settings
    /// @@
    /// @@     The current log settings.
    /// @@
    #[prost(map = "string, message", tag = "1")]
    pub settings: ::std::collections::HashMap<
        ::prost::alloc::string::String,
        log_settings_request::SettingValue,
    >,
}
/// Nested message and enum types in `LogSettingsRequest`.
pub mod log_settings_request {
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct SettingValue {
        #[prost(oneof = "setting_value::ParameterChoice", tags = "1, 2, 3")]
        pub parameter_choice: ::core::option::Option<setting_value::ParameterChoice>,
    }
    /// Nested message and enum types in `SettingValue`.
    pub mod setting_value {
        #[allow(clippy::derive_partial_eq_without_eq)]
        #[derive(Clone, PartialEq, ::prost::Oneof)]
        pub enum ParameterChoice {
            /// @@    .. cpp:var:: bool bool_param
            /// @@
            /// @@       A boolean parameter value.
            /// @@
            #[prost(bool, tag = "1")]
            BoolParam(bool),
            /// @@    .. cpp:var:: uint32 uint32_param
            /// @@
            /// @@       An uint32 parameter value.
            /// @@
            #[prost(uint32, tag = "2")]
            Uint32Param(u32),
            /// @@    .. cpp:var:: string string_param
            /// @@
            /// @@       A string parameter value.
            /// @@
            #[prost(string, tag = "3")]
            StringParam(::prost::alloc::string::String),
        }
    }
}
/// @@
/// @@.. cpp:var:: message LogSettingsResponse
/// @@
/// @@   Response message for LogSettings.
/// @@
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct LogSettingsResponse {
    /// @@  .. cpp:var:: map<string,SettingValue> settings
    /// @@
    /// @@     The current log settings.
    /// @@
    #[prost(map = "string, message", tag = "1")]
    pub settings: ::std::collections::HashMap<
        ::prost::alloc::string::String,
        log_settings_response::SettingValue,
    >,
}
/// Nested message and enum types in `LogSettingsResponse`.
pub mod log_settings_response {
    #[allow(clippy::derive_partial_eq_without_eq)]
    #[derive(Clone, PartialEq, ::prost::Message)]
    pub struct SettingValue {
        #[prost(oneof = "setting_value::ParameterChoice", tags = "1, 2, 3")]
        pub parameter_choice: ::core::option::Option<setting_value::ParameterChoice>,
    }
    /// Nested message and enum types in `SettingValue`.
    pub mod setting_value {
        #[allow(clippy::derive_partial_eq_without_eq)]
        #[derive(Clone, PartialEq, ::prost::Oneof)]
        pub enum ParameterChoice {
            /// @@    .. cpp:var:: bool bool_param
            /// @@
            /// @@       A boolean parameter value.
            /// @@
            #[prost(bool, tag = "1")]
            BoolParam(bool),
            /// @@    .. cpp:var:: uint32 uint32_param
            /// @@
            /// @@       An int32 parameter value.
            /// @@
            #[prost(uint32, tag = "2")]
            Uint32Param(u32),
            /// @@    .. cpp:var:: string string_param
            /// @@
            /// @@       A string parameter value.
            /// @@
            #[prost(string, tag = "3")]
            StringParam(::prost::alloc::string::String),
        }
    }
}
/// Generated client implementations.
pub mod grpc_inference_service_client {
    #![allow(unused_variables, dead_code, missing_docs, clippy::let_unit_value)]
    use tonic::codegen::*;
    use tonic::codegen::http::Uri;
    /// @@
    /// @@.. cpp:var:: service InferenceService
    /// @@
    /// @@   Inference Server GRPC endpoints.
    /// @@
    #[derive(Debug, Clone)]
    pub struct GrpcInferenceServiceClient<T> {
        inner: tonic::client::Grpc<T>,
    }
    impl GrpcInferenceServiceClient<tonic::transport::Channel> {
        /// Attempt to create a new client by connecting to a given endpoint.
        pub async fn connect<D>(dst: D) -> Result<Self, tonic::transport::Error>
        where
            D: std::convert::TryInto<tonic::transport::Endpoint>,
            D::Error: Into<StdError>,
        {
            let conn = tonic::transport::Endpoint::new(dst)?.connect().await?;
            Ok(Self::new(conn))
        }
    }
    impl<T> GrpcInferenceServiceClient<T>
    where
        T: tonic::client::GrpcService<tonic::body::BoxBody>,
        T::Error: Into<StdError>,
        T::ResponseBody: Body<Data = Bytes> + Send + 'static,
        <T::ResponseBody as Body>::Error: Into<StdError> + Send,
    {
        pub fn new(inner: T) -> Self {
            let inner = tonic::client::Grpc::new(inner);
            Self { inner }
        }
        pub fn with_origin(inner: T, origin: Uri) -> Self {
            let inner = tonic::client::Grpc::with_origin(inner, origin);
            Self { inner }
        }
        pub fn with_interceptor<F>(
            inner: T,
            interceptor: F,
        ) -> GrpcInferenceServiceClient<InterceptedService<T, F>>
        where
            F: tonic::service::Interceptor,
            T::ResponseBody: Default,
            T: tonic::codegen::Service<
                http::Request<tonic::body::BoxBody>,
                Response = http::Response<
                    <T as tonic::client::GrpcService<tonic::body::BoxBody>>::ResponseBody,
                >,
            >,
            <T as tonic::codegen::Service<
                http::Request<tonic::body::BoxBody>,
            >>::Error: Into<StdError> + Send + Sync,
        {
            GrpcInferenceServiceClient::new(InterceptedService::new(inner, interceptor))
        }
        /// Compress requests with the given encoding.
        ///
        /// This requires the server to support it otherwise it might respond with an
        /// error.
        #[must_use]
        pub fn send_compressed(mut self, encoding: CompressionEncoding) -> Self {
            self.inner = self.inner.send_compressed(encoding);
            self
        }
        /// Enable decompressing responses.
        #[must_use]
        pub fn accept_compressed(mut self, encoding: CompressionEncoding) -> Self {
            self.inner = self.inner.accept_compressed(encoding);
            self
        }
        /// @@  .. cpp:var:: rpc ServerLive(ServerLiveRequest) returns
        /// @@       (ServerLiveResponse)
        /// @@
        /// @@     Check liveness of the inference server.
        /// @@
        pub async fn server_live(
            &mut self,
            request: impl tonic::IntoRequest<super::ServerLiveRequest>,
        ) -> Result<tonic::Response<super::ServerLiveResponse>, tonic::Status> {
            self.inner
                .ready()
                .await
                .map_err(|e| {
                    tonic::Status::new(
                        tonic::Code::Unknown,
                        format!("Service was not ready: {}", e.into()),
                    )
                })?;
            let codec = tonic::codec::ProstCodec::default();
            let path = http::uri::PathAndQuery::from_static(
                "/inference.GRPCInferenceService/ServerLive",
            );
            self.inner.unary(request.into_request(), path, codec).await
        }
        /// @@  .. cpp:var:: rpc ServerReady(ServerReadyRequest) returns
        /// @@       (ServerReadyResponse)
        /// @@
        /// @@     Check readiness of the inference server.
        /// @@
        pub async fn server_ready(
            &mut self,
            request: impl tonic::IntoRequest<super::ServerReadyRequest>,
        ) -> Result<tonic::Response<super::ServerReadyResponse>, tonic::Status> {
            self.inner
                .ready()
                .await
                .map_err(|e| {
                    tonic::Status::new(
                        tonic::Code::Unknown,
                        format!("Service was not ready: {}", e.into()),
                    )
                })?;
            let codec = tonic::codec::ProstCodec::default();
            let path = http::uri::PathAndQuery::from_static(
                "/inference.GRPCInferenceService/ServerReady",
            );
            self.inner.unary(request.into_request(), path, codec).await
        }
        /// @@  .. cpp:var:: rpc ModelReady(ModelReadyRequest) returns
        /// @@       (ModelReadyResponse)
        /// @@
        /// @@     Check readiness of a model in the inference server.
        /// @@
        pub async fn model_ready(
            &mut self,
            request: impl tonic::IntoRequest<super::ModelReadyRequest>,
        ) -> Result<tonic::Response<super::ModelReadyResponse>, tonic::Status> {
            self.inner
                .ready()
                .await
                .map_err(|e| {
                    tonic::Status::new(
                        tonic::Code::Unknown,
                        format!("Service was not ready: {}", e.into()),
                    )
                })?;
            let codec = tonic::codec::ProstCodec::default();
            let path = http::uri::PathAndQuery::from_static(
                "/inference.GRPCInferenceService/ModelReady",
            );
            self.inner.unary(request.into_request(), path, codec).await
        }
        /// @@  .. cpp:var:: rpc ServerMetadata(ServerMetadataRequest) returns
        /// @@       (ServerMetadataResponse)
        /// @@
        /// @@     Get server metadata.
        /// @@
        pub async fn server_metadata(
            &mut self,
            request: impl tonic::IntoRequest<super::ServerMetadataRequest>,
        ) -> Result<tonic::Response<super::ServerMetadataResponse>, tonic::Status> {
            self.inner
                .ready()
                .await
                .map_err(|e| {
                    tonic::Status::new(
                        tonic::Code::Unknown,
                        format!("Service was not ready: {}", e.into()),
                    )
                })?;
            let codec = tonic::codec::ProstCodec::default();
            let path = http::uri::PathAndQuery::from_static(
                "/inference.GRPCInferenceService/ServerMetadata",
            );
            self.inner.unary(request.into_request(), path, codec).await
        }
        /// @@  .. cpp:var:: rpc ModelMetadata(ModelMetadataRequest) returns
        /// @@       (ModelMetadataResponse)
        /// @@
        /// @@     Get model metadata.
        /// @@
        pub async fn model_metadata(
            &mut self,
            request: impl tonic::IntoRequest<super::ModelMetadataRequest>,
        ) -> Result<tonic::Response<super::ModelMetadataResponse>, tonic::Status> {
            self.inner
                .ready()
                .await
                .map_err(|e| {
                    tonic::Status::new(
                        tonic::Code::Unknown,
                        format!("Service was not ready: {}", e.into()),
                    )
                })?;
            let codec = tonic::codec::ProstCodec::default();
            let path = http::uri::PathAndQuery::from_static(
                "/inference.GRPCInferenceService/ModelMetadata",
            );
            self.inner.unary(request.into_request(), path, codec).await
        }
        /// @@  .. cpp:var:: rpc ModelInfer(ModelInferRequest) returns
        /// @@       (ModelInferResponse)
        /// @@
        /// @@     Perform inference using a specific model.
        /// @@
        pub async fn model_infer(
            &mut self,
            request: impl tonic::IntoRequest<super::ModelInferRequest>,
        ) -> Result<tonic::Response<super::ModelInferResponse>, tonic::Status> {
            self.inner
                .ready()
                .await
                .map_err(|e| {
                    tonic::Status::new(
                        tonic::Code::Unknown,
                        format!("Service was not ready: {}", e.into()),
                    )
                })?;
            let codec = tonic::codec::ProstCodec::default();
            let path = http::uri::PathAndQuery::from_static(
                "/inference.GRPCInferenceService/ModelInfer",
            );
            self.inner.unary(request.into_request(), path, codec).await
        }
        /// @@  .. cpp:var:: rpc ModelStreamInfer(stream ModelInferRequest) returns
        /// @@       (stream ModelStreamInferResponse)
        /// @@
        /// @@     Perform streaming inference.
        /// @@
        pub async fn model_stream_infer(
            &mut self,
            request: impl tonic::IntoStreamingRequest<Message = super::ModelInferRequest>,
        ) -> Result<
            tonic::Response<tonic::codec::Streaming<super::ModelStreamInferResponse>>,
            tonic::Status,
        > {
            self.inner
                .ready()
                .await
                .map_err(|e| {
                    tonic::Status::new(
                        tonic::Code::Unknown,
                        format!("Service was not ready: {}", e.into()),
                    )
                })?;
            let codec = tonic::codec::ProstCodec::default();
            let path = http::uri::PathAndQuery::from_static(
                "/inference.GRPCInferenceService/ModelStreamInfer",
            );
            self.inner.streaming(request.into_streaming_request(), path, codec).await
        }
        /// @@  .. cpp:var:: rpc ModelConfig(ModelConfigRequest) returns
        /// @@       (ModelConfigResponse)
        /// @@
        /// @@     Get model configuration.
        /// @@
        pub async fn model_config(
            &mut self,
            request: impl tonic::IntoRequest<super::ModelConfigRequest>,
        ) -> Result<tonic::Response<super::ModelConfigResponse>, tonic::Status> {
            self.inner
                .ready()
                .await
                .map_err(|e| {
                    tonic::Status::new(
                        tonic::Code::Unknown,
                        format!("Service was not ready: {}", e.into()),
                    )
                })?;
            let codec = tonic::codec::ProstCodec::default();
            let path = http::uri::PathAndQuery::from_static(
                "/inference.GRPCInferenceService/ModelConfig",
            );
            self.inner.unary(request.into_request(), path, codec).await
        }
        /// @@  .. cpp:var:: rpc ModelStatistics(
        /// @@                     ModelStatisticsRequest)
        /// @@                   returns (ModelStatisticsResponse)
        /// @@
        /// @@     Get the cumulative inference statistics for a model.
        /// @@
        pub async fn model_statistics(
            &mut self,
            request: impl tonic::IntoRequest<super::ModelStatisticsRequest>,
        ) -> Result<tonic::Response<super::ModelStatisticsResponse>, tonic::Status> {
            self.inner
                .ready()
                .await
                .map_err(|e| {
                    tonic::Status::new(
                        tonic::Code::Unknown,
                        format!("Service was not ready: {}", e.into()),
                    )
                })?;
            let codec = tonic::codec::ProstCodec::default();
            let path = http::uri::PathAndQuery::from_static(
                "/inference.GRPCInferenceService/ModelStatistics",
            );
            self.inner.unary(request.into_request(), path, codec).await
        }
        /// @@  .. cpp:var:: rpc RepositoryIndex(RepositoryIndexRequest) returns
        /// @@       (RepositoryIndexResponse)
        /// @@
        /// @@     Get the index of model repository contents.
        /// @@
        pub async fn repository_index(
            &mut self,
            request: impl tonic::IntoRequest<super::RepositoryIndexRequest>,
        ) -> Result<tonic::Response<super::RepositoryIndexResponse>, tonic::Status> {
            self.inner
                .ready()
                .await
                .map_err(|e| {
                    tonic::Status::new(
                        tonic::Code::Unknown,
                        format!("Service was not ready: {}", e.into()),
                    )
                })?;
            let codec = tonic::codec::ProstCodec::default();
            let path = http::uri::PathAndQuery::from_static(
                "/inference.GRPCInferenceService/RepositoryIndex",
            );
            self.inner.unary(request.into_request(), path, codec).await
        }
        /// @@  .. cpp:var:: rpc RepositoryModelLoad(RepositoryModelLoadRequest) returns
        /// @@       (RepositoryModelLoadResponse)
        /// @@
        /// @@     Load or reload a model from a repository.
        /// @@
        pub async fn repository_model_load(
            &mut self,
            request: impl tonic::IntoRequest<super::RepositoryModelLoadRequest>,
        ) -> Result<tonic::Response<super::RepositoryModelLoadResponse>, tonic::Status> {
            self.inner
                .ready()
                .await
                .map_err(|e| {
                    tonic::Status::new(
                        tonic::Code::Unknown,
                        format!("Service was not ready: {}", e.into()),
                    )
                })?;
            let codec = tonic::codec::ProstCodec::default();
            let path = http::uri::PathAndQuery::from_static(
                "/inference.GRPCInferenceService/RepositoryModelLoad",
            );
            self.inner.unary(request.into_request(), path, codec).await
        }
        /// @@  .. cpp:var:: rpc RepositoryModelUnload(RepositoryModelUnloadRequest)
        /// @@       returns (RepositoryModelUnloadResponse)
        /// @@
        /// @@     Unload a model.
        /// @@
        pub async fn repository_model_unload(
            &mut self,
            request: impl tonic::IntoRequest<super::RepositoryModelUnloadRequest>,
        ) -> Result<
            tonic::Response<super::RepositoryModelUnloadResponse>,
            tonic::Status,
        > {
            self.inner
                .ready()
                .await
                .map_err(|e| {
                    tonic::Status::new(
                        tonic::Code::Unknown,
                        format!("Service was not ready: {}", e.into()),
                    )
                })?;
            let codec = tonic::codec::ProstCodec::default();
            let path = http::uri::PathAndQuery::from_static(
                "/inference.GRPCInferenceService/RepositoryModelUnload",
            );
            self.inner.unary(request.into_request(), path, codec).await
        }
        /// @@  .. cpp:var:: rpc SystemSharedMemoryStatus(
        /// @@                     SystemSharedMemoryStatusRequest)
        /// @@                   returns (SystemSharedMemoryStatusRespose)
        /// @@
        /// @@     Get the status of all registered system-shared-memory regions.
        /// @@
        pub async fn system_shared_memory_status(
            &mut self,
            request: impl tonic::IntoRequest<super::SystemSharedMemoryStatusRequest>,
        ) -> Result<
            tonic::Response<super::SystemSharedMemoryStatusResponse>,
            tonic::Status,
        > {
            self.inner
                .ready()
                .await
                .map_err(|e| {
                    tonic::Status::new(
                        tonic::Code::Unknown,
                        format!("Service was not ready: {}", e.into()),
                    )
                })?;
            let codec = tonic::codec::ProstCodec::default();
            let path = http::uri::PathAndQuery::from_static(
                "/inference.GRPCInferenceService/SystemSharedMemoryStatus",
            );
            self.inner.unary(request.into_request(), path, codec).await
        }
        /// @@  .. cpp:var:: rpc SystemSharedMemoryRegister(
        /// @@                     SystemSharedMemoryRegisterRequest)
        /// @@                   returns (SystemSharedMemoryRegisterResponse)
        /// @@
        /// @@     Register a system-shared-memory region.
        /// @@
        pub async fn system_shared_memory_register(
            &mut self,
            request: impl tonic::IntoRequest<super::SystemSharedMemoryRegisterRequest>,
        ) -> Result<
            tonic::Response<super::SystemSharedMemoryRegisterResponse>,
            tonic::Status,
        > {
            self.inner
                .ready()
                .await
                .map_err(|e| {
                    tonic::Status::new(
                        tonic::Code::Unknown,
                        format!("Service was not ready: {}", e.into()),
                    )
                })?;
            let codec = tonic::codec::ProstCodec::default();
            let path = http::uri::PathAndQuery::from_static(
                "/inference.GRPCInferenceService/SystemSharedMemoryRegister",
            );
            self.inner.unary(request.into_request(), path, codec).await
        }
        /// @@  .. cpp:var:: rpc SystemSharedMemoryUnregister(
        /// @@                     SystemSharedMemoryUnregisterRequest)
        /// @@                   returns (SystemSharedMemoryUnregisterResponse)
        /// @@
        /// @@     Unregister a system-shared-memory region.
        /// @@
        pub async fn system_shared_memory_unregister(
            &mut self,
            request: impl tonic::IntoRequest<super::SystemSharedMemoryUnregisterRequest>,
        ) -> Result<
            tonic::Response<super::SystemSharedMemoryUnregisterResponse>,
            tonic::Status,
        > {
            self.inner
                .ready()
                .await
                .map_err(|e| {
                    tonic::Status::new(
                        tonic::Code::Unknown,
                        format!("Service was not ready: {}", e.into()),
                    )
                })?;
            let codec = tonic::codec::ProstCodec::default();
            let path = http::uri::PathAndQuery::from_static(
                "/inference.GRPCInferenceService/SystemSharedMemoryUnregister",
            );
            self.inner.unary(request.into_request(), path, codec).await
        }
        /// @@  .. cpp:var:: rpc CudaSharedMemoryStatus(
        /// @@                     CudaSharedMemoryStatusRequest)
        /// @@                   returns (CudaSharedMemoryStatusRespose)
        /// @@
        /// @@     Get the status of all registered CUDA-shared-memory regions.
        /// @@
        pub async fn cuda_shared_memory_status(
            &mut self,
            request: impl tonic::IntoRequest<super::CudaSharedMemoryStatusRequest>,
        ) -> Result<
            tonic::Response<super::CudaSharedMemoryStatusResponse>,
            tonic::Status,
        > {
            self.inner
                .ready()
                .await
                .map_err(|e| {
                    tonic::Status::new(
                        tonic::Code::Unknown,
                        format!("Service was not ready: {}", e.into()),
                    )
                })?;
            let codec = tonic::codec::ProstCodec::default();
            let path = http::uri::PathAndQuery::from_static(
                "/inference.GRPCInferenceService/CudaSharedMemoryStatus",
            );
            self.inner.unary(request.into_request(), path, codec).await
        }
        /// @@  .. cpp:var:: rpc CudaSharedMemoryRegister(
        /// @@                     CudaSharedMemoryRegisterRequest)
        /// @@                   returns (CudaSharedMemoryRegisterResponse)
        /// @@
        /// @@     Register a CUDA-shared-memory region.
        /// @@
        pub async fn cuda_shared_memory_register(
            &mut self,
            request: impl tonic::IntoRequest<super::CudaSharedMemoryRegisterRequest>,
        ) -> Result<
            tonic::Response<super::CudaSharedMemoryRegisterResponse>,
            tonic::Status,
        > {
            self.inner
                .ready()
                .await
                .map_err(|e| {
                    tonic::Status::new(
                        tonic::Code::Unknown,
                        format!("Service was not ready: {}", e.into()),
                    )
                })?;
            let codec = tonic::codec::ProstCodec::default();
            let path = http::uri::PathAndQuery::from_static(
                "/inference.GRPCInferenceService/CudaSharedMemoryRegister",
            );
            self.inner.unary(request.into_request(), path, codec).await
        }
        /// @@  .. cpp:var:: rpc CudaSharedMemoryUnregister(
        /// @@                     CudaSharedMemoryUnregisterRequest)
        /// @@                   returns (CudaSharedMemoryUnregisterResponse)
        /// @@
        /// @@     Unregister a CUDA-shared-memory region.
        /// @@
        pub async fn cuda_shared_memory_unregister(
            &mut self,
            request: impl tonic::IntoRequest<super::CudaSharedMemoryUnregisterRequest>,
        ) -> Result<
            tonic::Response<super::CudaSharedMemoryUnregisterResponse>,
            tonic::Status,
        > {
            self.inner
                .ready()
                .await
                .map_err(|e| {
                    tonic::Status::new(
                        tonic::Code::Unknown,
                        format!("Service was not ready: {}", e.into()),
                    )
                })?;
            let codec = tonic::codec::ProstCodec::default();
            let path = http::uri::PathAndQuery::from_static(
                "/inference.GRPCInferenceService/CudaSharedMemoryUnregister",
            );
            self.inner.unary(request.into_request(), path, codec).await
        }
        /// @@  .. cpp:var:: rpc TraceSetting(TraceSettingRequest)
        /// @@                   returns (TraceSettingResponse)
        /// @@
        /// @@     Update and get the trace setting of the Triton server.
        /// @@
        pub async fn trace_setting(
            &mut self,
            request: impl tonic::IntoRequest<super::TraceSettingRequest>,
        ) -> Result<tonic::Response<super::TraceSettingResponse>, tonic::Status> {
            self.inner
                .ready()
                .await
                .map_err(|e| {
                    tonic::Status::new(
                        tonic::Code::Unknown,
                        format!("Service was not ready: {}", e.into()),
                    )
                })?;
            let codec = tonic::codec::ProstCodec::default();
            let path = http::uri::PathAndQuery::from_static(
                "/inference.GRPCInferenceService/TraceSetting",
            );
            self.inner.unary(request.into_request(), path, codec).await
        }
        /// @@  .. cpp:var:: rpc LogSettings(LogSettingsRequest)
        /// @@                   returns (LogSettingsResponse)
        /// @@
        /// @@     Update and get the log settings of the Triton server.
        /// @@
        pub async fn log_settings(
            &mut self,
            request: impl tonic::IntoRequest<super::LogSettingsRequest>,
        ) -> Result<tonic::Response<super::LogSettingsResponse>, tonic::Status> {
            self.inner
                .ready()
                .await
                .map_err(|e| {
                    tonic::Status::new(
                        tonic::Code::Unknown,
                        format!("Service was not ready: {}", e.into()),
                    )
                })?;
            let codec = tonic::codec::ProstCodec::default();
            let path = http::uri::PathAndQuery::from_static(
                "/inference.GRPCInferenceService/LogSettings",
            );
            self.inner.unary(request.into_request(), path, codec).await
        }
    }
}