batch size

tokens/second

p90

p95

p99

1

26.2867

2.03927

2.50127

3.38444

2

37.9656

2.66554

3.13718

4.35343

4

52.68

3.90231

4.27135

6.70392

8

60.0354

6.66561

7.94382

12.7633

batch size

tokens/second

p90

p95

p99

1

31.9811

2.33799

2.66042

3.81389

2

42.7697

2.92146

3.48803

4.87088

4

55.6321

4.42112

5.65174

7.68267

8

63.8819

7.67295

9.85235

12.8664

batch size

tokens/second

p90

p95

p99

1

26.3775

1.34108

1.54733

1.99489

2

38.9406

1.6354

1.87501

2.2296

4

56.8026

2.16781

2.43267

2.74134

8

74.5635

3.30279

3.59166

4.28577

batch size

tokens/second

p90

p95

p99

1

37.3683

1.04883

1.2315

1.5244

2

56.919

1.27984

1.44713

1.80017

4

84.6404

1.62568

1.8017

2.21461

8

116.29

2.32152

2.69288

3.06221

batch size

tokens/second

p90

p95

p99

1

26.407

1.39359

1.59803

2.0832

2

38.9544

1.70536

1.89963

2.53018

4

57.3626

2.17563

2.41663

4.14745

8

74.4845

3.24898

3.77144

7.65627

batch size

tokens/second

p90

p95

p99

1

25.9981

0.996788

1.16798

1.65174

2

37.7592

1.23002

1.43918

2.28275

4

55.8361

1.59303

1.92639

2.96886

8

72.8569

2.47273

3.09559

4.60961

batch size

tokens/second

p90

p95

p99

1

25.0178

2.16171

2.67937

3.57496

2

35.7852

2.8741

3.43384

4.825

4

45.7635

4.75694

5.46036

8.43625

8

53.6928

7.49429

9.33626

15.9536

batch size

tokens/second

p90

p95

p99

1

30.4228

2.45499

2.8447

4.16917

2

39.371

3.23598

3.9612

5.80284

4

47.5513

5.20845

6.5702

9.05081

8

53.4489

9.45831

12.3315

16.7165

batch size

tokens/second

p90

p95

p99

1

25.7329

1.4008

1.59731

2.02982

2

37.3419

1.70973

1.97817

2.38832

4

52.8377

2.39732

2.73125

3.28759

8

62.3088

3.89276

4.19171

5.01999

batch size

tokens/second

p90

p95

p99

1

37.6181

1.06453

1.2618

1.56666

2

54.3727

1.34588

1.54159

1.90145

4

77.2692

1.85304

2.06099

2.62032

8

100.463

2.67849

3.19095

3.68078

batch size

tokens/second

p90

p95

p99

1

25.6851

1.45086

1.65187

2.14367

2

37.6205

1.77873

2.00517

2.71895

4

52.6492

2.39175

2.70523

4.71649

8

62.1082

3.8764

4.39479

9.33342

batch size

tokens/second

p90

p95

p99

1

26.3125

1.00717

1.19257

1.67369

2

36.9222

1.2762

1.478

2.46823

4

51.398

1.83249

2.24098

3.33602

8

63.8143

2.85154

3.58795

5.41236

batch size

tokens/second

p90

p95

p99

1

24.8964

2.12924

2.65001

3.58206

2

34.9882

2.98058

3.54244

5.17292

4

44.407

4.79422

5.67429

8.66048

8

52.0275

7.6554

9.58992

15.6379

batch size

tokens/second

p90

p95

p99

1

29.9773

2.48201

2.85844

4.27288

2

38.6565

3.3019

4.04395

6.12123

4

45.7503

5.44284

7.03912

9.69829

8

51.1056

9.83193

12.5469

16.8656

batch size

tokens/second

p90

p95

p99

1

25.3765

1.38744

1.56635

2.01276

2

37.2191

1.7271

2.00251

2.42118

4

51.1486

2.51382

2.8324

3.51729

8

59.8422

4.07464

4.40873

5.24835

batch size

tokens/second

p90

p95

p99

1

36.2303

1.0951

1.27495

1.57815

2

53.9788

1.35253

1.54013

1.93965

4

76.3488

1.85225

2.07805

2.64824

8

96.3217

2.80936

3.31854

3.90351

batch size

tokens/second

p90

p95

p99

1

25.2758

1.44721

1.65356

2.15285

2

37.604

1.77375

2.01242

2.72198

4

51.4024

2.49608

2.79586

5.08613

8

59.5006

4.04908

4.63766

9.81065

batch size

tokens/second

p90

p95

p99

1

25.2419

1.03367

1.22135

1.71075

2

36.4417

1.27991

1.50347

2.44608

4

50.6761

1.8483

2.28897

3.48173

8

61.1923

2.97418

3.84112

5.69605

batch size

tokens/second

p90

p95

p99

1

23.864

2.21488

2.74259

3.76037

2

33.5527

3.10486

3.74949

5.343

4

42.1649

5.07062

5.93531

9.05

8

47.4944

8.55144

10.6804

18.5123

batch size

tokens/second

p90

p95

p99

1

28.6128

2.60506

3.0003

4.4652

2

36.6462

3.51057

4.29037

6.38079

4

43.646

5.66035

7.43962

10.2525

8

46.5824

10.8355

14.4172

19.4719

batch size

tokens/second

p90

p95

p99

1

24.1934

1.4668

1.6551

2.11026

2

35.5399

1.81347

2.08718

2.53916

4

47.9159

2.66117

2.97279

3.50095

8

57.1626

4.3184

4.66154

5.64512

batch size

tokens/second

p90

p95

p99

1

34.9025

1.13927

1.33301

1.64506

2

51.477

1.42015

1.62161

2.02865

4

71.5458

2.03029

2.23385

2.80834

8

91.6256

3.00349

3.51311

4.12845

batch size

tokens/second

p90

p95

p99

1

24.0672

1.5234

1.74705

2.25971

2

35.6375

1.8885

2.14569

2.97039

4

47.8865

2.65449

2.95025

5.46151

8

56.8241

4.30345

4.90771

10.5702

batch size

tokens/second

p90

p95

p99

1

24.3206

1.07742

1.26691

1.793

2

34.7435

1.35411

1.58727

2.62002

4

48.3788

1.91256

2.35622

3.66184

8

57.9614

3.2078

4.05819

6.1864

batch size

tokens/second

p90

p95

p99

1

40.5707

1.30604

1.5894

2.16364

2

56.9553

1.79082

2.16168

3.29733

4

66.8099

3.26993

3.64887

6.21649

8

62.5757

6.792

8.24721

13.8332

batch size

tokens/second

p90

p95

p99

1

49.4655

1.48434

1.73773

2.54071

2

61.9468

2.11053

2.53549

3.89271

4

66.7364

4.09326

4.85237

7.36323

8

61.9911

8.39187

11.1865

14.189

batch size

tokens/second

p90

p95

p99

1

40.4369

0.867933

0.983312

1.27003

2

58.9499

1.08901

1.2567

1.5336

4

77.0764

1.69687

1.93364

2.22511

8

79.8035

3.2676

3.61598

4.42012

batch size

tokens/second

p90

p95

p99

1

58.1328

0.671243

0.787934

0.980829

2

87.3839

0.83912

0.962738

1.19282

4

118.819

1.23386

1.37922

1.73483

8

133.943

2.14844

2.5295

2.95827

batch size

tokens/second

p90

p95

p99

1

40.4461

0.897417

1.02884

1.32677

2

59.6298

1.12109

1.25972

1.7518

4

77.4412

1.68057

1.88498

3.61804

8

79.0987

3.16789

3.72364

8.32152

batch size

tokens/second

p90

p95

p99

1

40.7501

0.625767

0.745007

1.02009

2

58.8772

0.795955

0.932173

1.55014

4

79.4899

1.19318

1.46917

2.35335

8

83.196

2.30013

2.96352

4.70573

batch size

tokens/second

p90

p95

p99

1

14.9059

4.18064

5.55622

8.90397

2

13.6982

8.77877

11.1217

18.41

4

11.9895

20.2857

23.3168

42.145

8

9.84107

45.3629

55.302

99.5216

batch size

tokens/second

p90

p95

p99

1

15.731

5.57288

6.65737

11.7328

2

13.4258

10.9427

14.2988

21.9515

4

11.1191

24.9354

34.4626

52.6908

8

9.31464

56.1604

76.3938

104.507

batch size

tokens/second

p90

p95

p99

1

17.9065

2.14465

2.66442

3.96079

2

17.6863

4.13346

5.24532

6.7035

4

16.281

8.86584

10.5843

12.674

8

13.819

19.8851

21.9904

27.6311

batch size

tokens/second

p90

p95

p99

1

26.7904

1.63459

2.00438

2.7469

2

27.7218

3.06423

3.66466

5.05088

4

25.8234

6.25622

7.28332

9.68234

8

22.6921

13.3635

15.8901

18.9904

batch size

tokens/second

p90

p95

p99

1

17.3311

2.3286

2.87607

4.3078

2

17.2567

4.36889

5.3378

7.67524

4

15.9637

8.94096

10.3726

23.2293

8

13.4777

19.4014

23.5091

56.2237

batch size

tokens/second

p90

p95

p99

1

18.8599

1.44669

1.87181

3.1101

2

19.022

2.87861

3.5337

7.27692

4

17.3604

5.93223

7.70771

14.4663

8

14.1413

14.1156

18.7657

30.8777

batch size

tokens/second

p90

p95

p99

1

24.8926

2.14594

2.67499

3.60681

2

34.6774

2.99878

3.67241

5.14107

4

43.0674

5.10826

5.87656

9.39341

8

47.3776

8.54803

10.6197

17.5638

batch size

tokens/second

p90

p95

p99

1

29.8693

2.51427

2.89999

4.30795

2

38.044

3.39933

4.15936

6.2249

4

43.6223

5.74422

7.59899

10.6489

8

45.0687

11.1592

14.7241

20.0668

batch size

tokens/second

p90

p95

p99

1

25.3254

1.40709

1.59688

2.0528

2

36.817

1.74851

2.02427

2.45473

4

50.5628

2.54396

2.91978

3.61169

8

56.0985

4.47452

4.82638

5.72361

batch size

tokens/second

p90

p95

p99

1

36.8149

1.08212

1.27069

1.57721

2

53.7507

1.37057

1.56666

1.94615

4

74.8121

1.90943

2.13149

2.75404

8

91.2649

3.03928

3.61824

4.19196

batch size

tokens/second

p90

p95

p99

1

25.3073

1.45916

1.66434

2.1714

2

37.2553

1.80097

2.03974

2.80161

4

50.3437

2.58562

2.94337

5.41708

8

56.0202

4.39519

5.0318

10.5843

batch size

tokens/second

p90

p95

p99

1

25.6837

1.01961

1.20561

1.69398

2

36.3235

1.30864

1.53248

2.54312

4

49.6179

1.88027

2.28496

3.55785

8

58.6442

3.15507

4.11201

6.14629

batch size

tokens/second

p90

p95

p99

1

34.0965

1.58011

1.96628

2.72448

2

46.4873

2.26697

2.71925

3.91062

4

55.8697

4.02463

4.48315

7.21816

8

62.8854

6.56656

8.19178

12.6974

batch size

tokens/second

p90

p95

p99

1

40.779

1.86284

2.15408

3.22027

2

50.1581

2.63038

3.16101

4.68046

4

57.2902

4.3511

5.57995

7.81723

8

62.8918

8.30041

10.1785

14.5662

batch size

tokens/second

p90

p95

p99

1

35.271

1.02293

1.16197

1.49121

2

49.5213

1.31475

1.52514

1.86395

4

66.6292

1.9028

2.17766

2.81436

8

73.0008

3.37777

3.61952

4.34075

batch size

tokens/second

p90

p95

p99

1

51.3997

0.784364

0.933197

1.1595

2

72.977

1.0184

1.17174

1.46658

4

97.3946

1.48676

1.64859

2.09218

8

120.295

2.30302

2.62656

3.18205

batch size

tokens/second

p90

p95

p99

1

35.1238

1.0647

1.21599

1.60668

2

49.6636

1.37161

1.55412

2.12787

4

66.8252

1.90341

2.14164

3.96884

8

72.9761

3.32665

3.78859

8.20151

batch size

tokens/second

p90

p95

p99

1

35.956

0.73739

0.878487

1.25711

2

49.3781

0.963772

1.14114

1.93997

4

65.3594

1.4497

1.79878

2.6903

8

78.4195

2.40052

2.92004

4.53465