Commit Graph

Select branches

Hide Pull Requests

bf16_metal

bug_q4k

clippy-1.85

conv-transpose-groups

conv1d-algo

copy-multi-metal

copy2d-metal

cuda-conv-tr1d

cuda-graph-exp

cudarc-12-6

cudarc_freedom

ddpg

dependabot/cargo/gemm-0.18.0

dependabot/cargo/imageproc-0.25.0

dependabot/cargo/metal-0.28.0

dependabot/cargo/yew-0.21.0

dependabot/cargo/yew-agent-0.3.0

einsum-custom-op

faster-gemv

fix-1.86

fix_mkl_feature

gh-pages

hf-papers

improve-sampling

initializer

ivarflakstad/metal-fenceless

ivarflakstad/metal-fill

ivarflakstad/metal-reduce-2

ivarflakstad/metal-where-cond-2

linear-transpose

llama-v3-mp

llama2-wasm-fix

main

marian-tok

matmul-slowness

meshgrid-fix

metal-fp8-fun

metal-gemm

metal-gemm-testing

metal-mfa-bfloat

metal-precompile

metal2-tmp

metal4-m3

metal4-mfa

metal4.5

metal4.6

metal4.7

metal4.7-mps

metal4_arc

metal5

metal_heap

mkl_link_freedom

moondream

operators-argmin-argmax-leakyrelu

opt-attn-mask

phi2-gguf

precompile_metal

qmm-fix2

qmm-pad-fix

remove_wrapper_bench

smollm

sort

spkemb

tei_cudarc_freedom

tmp-metal-span

tmp4

tmp5

tmp_broken_metal

tmp_no_rotary

tmpgemm

tmpm4

vocos

w-uncond

wasm-llama2-tweaks

#1

#10

#100

#1000

#1001

#1002

#1004

#1007

#1009

#101

#1010

#1011

#1012

#1013

#1014

#1015

#1016

#1017

#1018

#1019

#102

#1020

#1021

#1022

#1023

#1024

#1026

#1028

#1029

#103

#1030

#1031

#1033

#1035

#1037

#1038

#1039

#104

#1041

#1042

#1045

#1046

#1047

#1049

#105

#1050

#1051

#1052

#1053

#1054

#1056

#1057

#1058

#106

#1063

#1064

#1066

#1067

#1068

#1069

#107

#1071

#1072

#1073

#1074

#1076

#108

#1080

#1082

#1083

#1084

#1085

#1086

#1088

#1089

#109

#1090

#1093

#1094

#1096

#1097

#1098

#1099

#11

#110

#1100

#1101

#1102

#1106

#1108

#1109

#111

#1110

#1111

#1112

#1114

#1115

#1117

#1119

#112

#1120

#1121

#1122

#1123

#1124

#1125

#1126

#1127

#1128

#1129

#113

#1130

#1131

#1132

#1134

#1135

#1136

#1137

#114

#1140

#1141

#1142

#1143

#1144

#1145

#1146

#1147

#1148

#115

#1150

#1152

#1154

#1155

#1157

#1158

#1159

#116

#1160

#1161

#1164

#1166

#1167

#1169

#117

#1170

#1171

#1172

#1174

#1175

#1176

#1178

#1179

#118

#1180

#1183

#1184

#1187

#1189

#119

#1190

#1192

#1193

#1194

#1196

#1197

#1198

#12

#120

#1200

#1201

#1202

#1203

#1204

#1205

#1206

#1206

#1207

#1208

#1209

#121

#1210

#1211

#1213

#1214

#1215

#1216

#1217

#1218

#1219

#122

#1220

#1221

#1222

#1225

#1226

#1228

#123

#1230

#1233

#1234

#1236

#1237

#124

#1242

#1243

#1244

#1245

#1246

#1248

#125

#1251

#1252

#1253

#1254

#1255

#1257

#1258

#1259

#126

#1260

#1261

#1262

#1264

#1265

#1266

#1267

#1268

#1269

#127

#1270

#1271

#1272

#1273

#1275

#1276

#1277

#1278

#128

#1282

#1283

#1284

#1285

#1287

#1288

#129

#1290

#1291

#1294

#1295

#1296

#1298

#13

#130

#1300

#1303

#1306

#1308

#1309

#131

#1310

#1312

#1313

#1315

#1316

#1317

#1318

#132

#1320

#1321

#1322

#1323

#1324

#1326

#133

#1332

#1333

#1334

#1335

#1336

#1337

#1338

#134

#1340

#1341

#1346

#1347

#135

#1350

#1353

#1354

#1356

#1358

#136

#1360

#1362

#1363

#1366

#1369

#137

#1370

#1372

#1374

#1376

#1377

#138

#1381

#1384

#1386

#1387

#1388

#1388

#1389

#139

#1390

#1393

#1395

#1397

#1398

#14

#140

#1400

#1401

#1402

#1406

#1407

#1408

#141

#1410

#1411

#1412

#1413

#1413

#1418

#1418

#142

#1420

#1424

#1425

#1426

#1429

#143

#1430

#1432

#1433

#1434

#1436

#1437

#1438

#1438

#144

#1442

#1443

#1444

#1446

#1447

#1449

#145

#1450

#1451

#1452

#1453

#1455

#1458

#1459

#146

#1461

#1464

#1465

#1466

#1466

#1467

#1468

#147

#1470

#1470

#1471

#1472

#1473

#1474

#1475

#1476

#1476

#1478

#1479

#148

#1481

#1483

#1483

#1484

#1485

#1487

#1488

#1489

#149

#1490

#1491

#1492

#1493

#1494

#1495

#1496

#1498

#1499

#15

#150

#1500

#1501

#1501

#1502

#1503

#1504

#1505

#1507

#151

#1511

#1512

#1513

#1514

#1515

#1515

#1517

#1518

#152

#1520

#1523

#1524

#1525

#1526

#1529

#153

#1530

#1530

#1531

#1533

#1534

#1535

#1536

#1538

#154

#1540

#1541

#1543

#1544

#1545

#1546

#1549

#1549

#155

#1551

#1551

#1553

#1554

#1555

#1556

#1557

#1557

#1558

#1559

#156

#1560

#1561

#1562

#1565

#1567

#1569

#157

#1571

#1571

#1572

#1573

#1576

#1577

#1579

#1579

#158

#1580

#1581

#1581

#1582

#1583

#1586

#1587

#1589

#159

#1590

#1590

#1591

#1592

#1594

#1595

#1598

#1598

#16

#160

#1601

#1602

#1604

#1605

#1605

#1606

#161

#1610

#1611

#1611

#1614

#1616

#1616

#1617

#1619

#162

#1627

#1628

#163

#1635

#1635

#1636

#1638

#164

#1641

#1642

#1648

#165

#1650

#1651

#1654

#1655

#1655

#1656

#1656

#1657

#1658

#166

#1660

#1661

#1662

#1662

#1666

#1667

#1668

#1669

#167

#1670

#1671

#1672

#1674

#1678

#168

#1680

#1681

#1682

#1684

#1685

#1686

#1687

#1688

#1689

#169

#1690

#1691

#1692

#1693

#1694

#1696

#1697

#17

#170

#1702

#1703

#1704

#1705

#1706

#1707

#1709

#171

#1710

#1711

#1712

#1715

#1717

#1719

#172

#1722

#1724

#1726

#1727

#1728

#173

#1730

#1731

#1732

#1734

#1736

#1736

#1738

#174

#1740

#1741

#1742

#1743

#1744

#1745

#1747

#1747

#1749

#175

#1753

#1754

#1756

#1758

#176

#1760

#1766

#1767

#1768

#177

#1770

#1771

#1772

#1775

#1776

#1777

#1778

#1779

#178

#1781

#1783

#1784

#1785

#1787

#1788

#179

#1790

#1791

#1792

#1794

#1795

#1796

#1797

#1799

#1799

#18

#180

#1800

#1804

#1805

#1806

#1806

#1807

#181

#1811

#1812

#1814

#1816

#1817

#1819

#182

#1821

#1822

#1823

#1824

#1825

#1826

#183

#1832

#1835

#1836

#1836

#1837

#184

#1840

#1843

#1845

#1847

#1848

#1848

#1849

#185

#1852

#1855

#1856

#1857

#1859

#186

#1860

#1861

#1862

#1863

#1864

#1865

#1866

#1867

#1868

#1869

#187

#1870

#1871

#1872

#1873

#1874

#1876

#188

#1880

#1880

#1884

#1885

#1886

#1888

#1888

#189

#1890

#1892

#1893

#1895

#1897

#1898

#1899

#19

#190

#1900

#1901

#1903

#1904

#1906

#1908

#1909

#191

#1910

#1913

#1915

#1919

#192

#1920

#1921

#1923

#1924

#1925

#1925

#1927

#1928

#1929

#193

#1932

#1933

#1934

#1935

#1937

#1938

#194

#1940

#1943

#1946

#1949

#195

#1950

#1951

#1952

#1954

#1955

#1957

#1958

#1959

#196

#1960

#1961

#1963

#1964

#1966

#1967

#1968

#1969

#197

#1970

#1972

#1973

#1976

#1977

#1978

#1979

#198

#1980

#1981

#1983

#1984

#1985

#1986

#1987

#1989

#199

#1990

#1990

#1993

#1994

#1995

#1997

#1998

#1999

#2

#20

#200

#2000

#2001

#2002

#2003

#2004

#2005

#2008

#2009

#201

#2010

#2011

#2012

#2013

#2014

#2015

#2016

#2017

#2018

#202

#2021

#2022

#2023

#2024

#2026

#2028

#2029

#203

#2035

#2036

#2037

#2037

#2038

#2039

#204

#2043

#2044

#2045

#2047

#2048

#2049

#205

#2051

#2052

#2053

#2054

#2055

#2056

#2057

#2058

#206

#2060

#2061

#2061

#2062

#2063

#2064

#2066

#2067

#207

#2071

#2073

#2075

#2077

#2078

#208

#2080

#2083

#2084

#2084

#2085

#2086

#2087

#2088

#209

#2091

#2092

#2093

#2094

#2095

#2096

#2097

#2098

#2099

#21

#210

#2100

#2101

#2101

#2103

#2104

#2106

#2107

#211

#2111

#2113

#2114

#2116

#2117

#2118

#212

#2120

#2121

#2122

#2124

#2127

#213

#2132

#2133

#2134

#2135

#2137

#2138

#214

#2141

#2142

#2143

#2145

#2145

#215

#2150

#2155

#2156

#2157

#2159

#216

#2162

#2165

#2166

#2166

#217

#2172

#2174

#2176

#2178

#2179

#218

#2180

#2183

#2187

#2188

#2189

#219

#2190

#2191

#2193

#2194

#2195

#2199

#2199

#22

#220

#2200

#2202

#2203

#2205

#2206

#2207

#2209

#221

#2211

#2212

#2213

#2214

#222

#2220

#2220

#2222

#2223

#2225

#2225

#2227

#2229

#223

#2230

#2231

#2233

#2234

#2235

#2236

#2238

#224

#2240

#2240

#2244

#2246

#2247

#2248

#225

#2251

#2253

#2253

#2257

#226

#2260

#2262

#2263

#2263

#2268

#227

#2274

#2279

#228

#2284

#2285

#2285

#2288

#2288

#2289

#2289

#229

#2292

#2292

#2293

#2296

#2296

#2298

#2299

#23

#230

#2305

#2306

#2308

#231

#2311

#2314

#2314

#2315

#2316

#2317

#2318

#232

#2320

#2321

#2324

#2325

#2328

#2329

#233

#2332

#2333

#2334

#2335

#2336

#2337

#2339

#2340

#2345

#2346

#2346

#235

#2352

#2353

#2357

#2359

#236

#2362

#2363

#2364

#2365

#2367

#2368

#237

#2372

#2372

#2375

#2375

#2376

#2378

#2379

#238

#2380

#2381

#2382

#2383

#2384

#2386

#2387

#239

#2390

#2393

#2394

#2395

#2396

#2397

#2398

#2399

#24

#240

#2400

#2403

#2405

#2407

#2408

#2408

#241

#2411

#2414

#2415

#2416

#2416

#242

#2420

#2421

#2422

#2422

#2424

#2425

#2426

#2428

#2429

#243

#2430

#2431

#2432

#2433

#2434

#2435

#2436

#2437

#2438

#2439

#244

#2440

#2442

#2444

#2445

#245

#2451

#2452

#2454

#2455

#2456

#2457

#246

#2460

#2460

#2461

#2464

#2466

#2467

#2467

#2468

#2469

#247

#2470

#2471

#2473

#2474

#2475

#2477

#2479

#248

#2481

#2481

#2485

#2487

#2488

#2489

#249

#2490

#2491

#2493

#2494

#2495

#25

#250

#2500

#2503

#2504

#2505

#2507

#2508

#2509

#251

#2510

#2512

#2513

#2515

#2517

#2518

#2519

#252

#2521

#2522

#2523

#2524

#2526

#2527

#2527

#2528

#2529

#253

#2531

#2532

#2533

#2535

#2536

#2536

#2538

#2538

#2539

#254

#2541

#2542

#2542

#2543

#2544

#2544

#2545

#2546

#2547

#2548

#255

#2550

#2551

#2553

#2555

#2556

#2558

#2559

#256

#2560

#2562

#2562

#2563

#2565

#2565

#2567

#2568

#257

#2572

#2576

#2577

#2578

#2579

#258

#2580

#2581

#2582

#2584

#2587

#2589

#259

#2590

#2591

#2595

#2596

#26

#260

#2600

#2601

#2601

#2603

#2603

#2606

#2608

#261

#2612

#2613

#2615

#2615

#2616

#2617

#2618

#262

#2620

#2623

#2624

#2625

#2626

#2628

#2629

#263

#2630

#2639

#264

#2640

#2640

#2642

#2644

#2644

#2645

#2646

#2647

#2648

#2648

#2649

#265

#2650

#2653

#2655

#2656

#2658

#266

#2662

#2663

#2664

#2664

#267

#2670

#2672

#2675

#2676

#2677

#2678

#2679

#2679

#268

#2681

#2683

#2683

#2684

#2686

#2688

#2689

#269

#2690

#2691

#2693

#2694

#2695

#2696

#2699

#27

#270

#2701

#2703

#2704

#2704

#2707

#2708

#271

#2710

#2713

#2714

#2715

#2716

#2717

#2718

#272

#2720

#2722

#2722

#2723

#2724

#2728

#2729

#2729

#273

#2730

#2732

#2733

#2734

#2735

#2738

#274

#2740

#2741

#2742

#2743

#2744

#2745

#2745

#2747

#2748

#275

#2750

#2751

#2752

#2752

#2754

#2755

#2758

#2758

#2759

#276

#2760

#2762

#2765

#2765

#2768

#2768

#277

#2770

#2771

#2772

#2773

#2773

#2777

#2777

#2778

#278

#2780

#2783

#2783

#2785

#2785

#279

#2790

#2791

#2796

#2797

#28

#280

#2800

#2801

#2801

#2802

#2804

#2804

#2806

#2808

#2809

#281

#2810

#2811

#2813

#2813

#282

#2820

#2820

#2821

#2824

#2825

#2825

#2829

#283

#2833

#2834

#2835

#2837

#2838

#2838

#2839

#284

#2841

#2841

#2842

#2843

#2845

#285

#2855

#2857

#2857

#2858

#2859

#286

#2860

#2861

#2861

#2862

#2864

#2866

#2867

#2868

#2869

#287

#2871

#2872

#2878

#2878

#2879

#2879

#288

#2880

#2881

#2882

#2883

#2884

#2885

#2886

#2887

#2887

#2888

#2889

#289

#2890

#2892

#2894

#2895

#2896

#2897

#2898

#29

#290

#2900

#2901

#2902

#2903

#2903

#2904

#2905

#2906

#2906

#2908

#2909

#291

#2910

#2914

#2915

#2917

#2918

#2919

#2919

#292

#2920

#2920

#2921

#2922

#2923

#2924

#2925

#2926

#2927

#2928

#2929

#293

#2930

#2932

#2934

#2935

#2936

#2937

#2937

#2939

#294

#2940

#2942

#2943

#2943

#2946

#295

#2951

#2952

#2953

#2954

#2955

#2956

#2957

#2957

#2958

#2958

#296

#2960

#2963

#2964

#2964

#2968

#2969

#297

#2970

#2972

#2973

#2973

#2978

#2979

#298

#2980

#2981

#2982

#2983

#2983

#2987

#2989

#2989

#299

#2991

#2991

#2992

#2992

#2994

#2994

#2995

#2995

#2996

#2996

#3

#30

#300

#301

#302

#303

#304

#305

#306

#307

#308

#309

#31

#310

#311

#312

#314

#315

#316

#317

#318

#319

#32

#320

#321

#322

#323

#324

#325

#326

#327

#328

#33

#330

#331

#332

#333

#334

#335

#336

#337

#338

#339

#34

#340

#341

#342

#343

#345

#347

#349

#35

#351

#352

#355

#356

#36

#361

#362

#363

#365

#366

#367

#368

#37

#370

#371

#372

#373

#374

#375

#376

#377

#378

#379

#38

#382

#383

#384

#386

#388

#389

#39

#390

#392

#393

#394

#395

#396

#397

#398

#399

#4

#40

#400

#401

#403

#404

#405

#407

#408

#409

#41

#411

#412

#413

#414

#415

#417

#419

#42

#420

#421

#423

#425

#426

#427

#428

#429

#43

#430

#431

#433

#434

#435

#437

#438

#439

#44

#440

#441

#445

#447

#448

#449

#45

#450

#452

#453

#454

#455

#456

#457

#458

#459

#46

#463

#464

#465

#466

#468

#469

#47

#470

#471

#473

#474

#475

#476

#48

#480

#481

#482

#483

#486

#487

#488

#489

#49

#490

#491

#492

#493

#495

#496

#497

#498

#499

#5

#50

#500

#501

#502

#503

#504

#506

#507

#508

#509

#51

#510

#511

#512

#515

#516

#517

#518

#519

#52

#520

#522

#523

#524

#525

#526

#527

#528

#529

#53

#530

#532

#534

#535

#536

#537

#539

#54

#541

#542

#544

#545

#546

#548

#549

#55

#550

#551

#552

#553

#554

#555

#556

#557

#558

#559

#56

#560

#561

#563

#564

#565

#566

#568

#569

#57

#570

#571

#572

#573

#577

#578

#579

#58

#580

#582

#585

#586

#587

#588

#589

#59

#590

#591

#594

#595

#596

#597

#598

#599

#6

#60

#600

#601

#602

#603

#604

#605

#606

#607

#609

#61

#610

#611

#614

#615

#616

#617

#619

#62

#623

#624

#625

#627

#628

#629

#63

#630

#632

#634

#635

#638

#64

#640

#641

#643

#644

#645

#647

#648

#649

#65

#651

#652

#653

#654

#656

#657

#658

#659

#66

#661

#662

#664

#665

#666

#667

#668

#668

#669

#67

#670

#671

#672

#673

#674

#675

#676

#677

#678

#679

#68

#681

#682

#684

#686

#687

#688

#689

#69

#690

#692

#693

#694

#694

#697

#699

#7

#70

#700

#701

#702

#704

#705

#706

#707

#707

#708

#709

#71

#710

#711

#712

#713

#714

#715

#716

#717

#718

#72

#723

#724

#725

#726

#727

#728

#728

#729

#73

#730

#731

#732

#736

#737

#738

#74

#740

#741

#742

#743

#744

#745

#746

#747

#748

#749

#75

#751

#752

#753

#757

#758

#759

#76

#760

#761

#763

#764

#765

#766

#767

#768

#769

#77

#770

#771

#772

#773

#775

#776

#777

#779

#78

#780

#781

#782

#784

#785

#786

#787

#788

#789

#79

#790

#791

#792

#793

#794

#796

#797

#798

#799

#8

#80

#800

#801

#802

#804

#805

#808

#809

#81

#810

#812

#813

#814

#815

#816

#817

#819

#82

#820

#821

#822

#823

#824

#825

#826

#827

#828

#829

#83

#830

#831

#832

#833

#834

#835

#836

#837

#838

#839

#84

#840

#842

#843

#846

#847

#848

#85

#851

#853

#854

#856

#858

#859

#86

#860

#861

#862

#864

#865

#866

#867

#869

#87

#870

#872

#873

#874

#875

#876

#877

#879

#88

#880

#882

#884

#885

#886

#887

#888

#889

#89

#890

#892

#893

#895

#896

#897

#898

#899

#9

#90

#900

#901

#902

#903

#905

#907

#908

#91

#910

#911

#912

#913

#914

#915

#917

#918

#919

#92

#921

#922

#923

#924

#925

#926

#927

#929

#93

#930

#931

#932

#933

#934

#936

#937

#938

#939

#940

#943

#945

#946

#947

#948

#949

#95

#950

#951

#952

#953

#954

#955

#956

#957

#958

#96

#961

#962

#963

#964

#965

#966

#968

#969

#97

#970

#970

#971

#972

#974

#976

#977

#98

#980

#982

#983

#984

#985

#986

#988

#99

#991

#992

#994

#995

#996

#997

#998

#999

0.5.1

0.6.0

0.7.0

0.7.1

0.7.2

0.8.0

0.8.1

0.8.2

0.8.3

0.8.4

0.9.0

0.9.0-alpha.1

0.9.0-alpha.2

0.9.0-alpha.3

0.9.0-alpha.4

0.9.1

Mono Color

• 9694671bbf Not implementing quantized. Nicolas Patry 2024-01-15 18:00:43 +01:00
• 3dbf65ef20 Rebase after phi2 merge + fix replit default to CPU. Nicolas Patry 2024-01-15 17:52:49 +01:00
• b2db5adf82 Bad code removal. Nicolas Patry 2024-01-15 17:25:06 +01:00
• 9ef040338d After rebase. Nicolas Patry 2024-01-11 17:17:55 +01:00
• 3aefc709c7 Cleanup the fence. Nicolas Patry 2024-01-05 21:57:07 +01:00
• c8c603ce96 Removing the fences speeds everything up and *is* correct this time... Nicolas Patry 2024-01-05 19:26:30 +01:00
• 61ad8d91cc Fix the rebase. Nicolas Patry 2024-01-05 14:31:39 +01:00
• 2cd1e59c9e Cleanup. Nicolas Patry 2024-01-05 14:28:08 +01:00
• 9c4b4f0da0 Metal quantized modifications proposal. Nicolas Patry 2023-11-18 14:49:30 +01:00
• 5637f86040 Update yew requirement from 0.20.0 to 0.21.0 dependabot/cargo/yew-0.21.0 dependabot[bot] 2024-01-15 12:25:36 +00:00
• ea36f3b11f Use the new phi model by default. (#1589) Laurent Mazare 2024-01-15 12:30:27 +01:00
• 79478ff5a1 Seed should be updated by random kernel result. Ivar Flakstad 2024-01-14 18:10:54 +01:00
• 86b7c01b30 Update gemm to the latest version. (#1587) Laurent Mazare 2024-01-15 09:44:51 +01:00
• bdd8107fda Expose the ndarray trait. (#1586) Laurent Mazare 2024-01-14 20:09:49 +01:00
• ecf88a6d38 Merge branch 'main' into ivarflakstad/metal-prng Ivar Flakstad 2024-01-14 17:10:54 +01:00
• e6d86b0819 Add the pow operator. (#1583) Laurent Mazare 2024-01-13 20:24:06 +01:00
• 88618255cb Fix the rotary embeddings for the new phi implementation. (#1582) Laurent Mazare 2024-01-13 19:44:41 +01:00
• 539ead927a Update the Phi model to use the updated architecture. (#1580) Laurent Mazare 2024-01-13 17:38:27 +01:00
• a46864bd56 Fix "Minimal Mamba" link in README. (#1577) SebastianRueClausen 2024-01-12 17:47:07 +01:00
• bafe95b660 Fix format. (#1576) Nicolas Patry 2024-01-12 14:23:17 +01:00
• a3d92ab226 Metal: Activate bfloat affine and add benchmark (#1543) ivarflakstad 2024-01-12 11:19:49 +01:00
• e90bcdcc7c Metal: f16 and bf16 where_cond + benchmark (#1545) ivarflakstad 2024-01-12 11:18:11 +01:00
• 8e06bfb4fd Mention VGG in the readme. (#1573) Laurent Mazare 2024-01-12 09:59:29 +01:00
• 6242276c09 Pin the revision used for phi-v2 + make it the default. (#1572) Laurent Mazare 2024-01-12 09:19:30 +01:00
• e06e8d0dbe fmt Ivar Flakstad 2024-01-12 07:26:42 +01:00
• 36ce0988c0 Merge branch 'main' into ivarflakstad/metal-fill Ivar Flakstad 2024-01-12 07:25:32 +01:00
• e63bb8661b Merge branch 'main' into ivarflakstad/metal-prng Ivar Flakstad 2024-01-12 07:19:58 +01:00
• 41915184bb Bugfix for dequantizing q5k layers. (#1569) Laurent Mazare 2024-01-11 23:15:11 +01:00
• c1876b8041 Merge pull request #1567 from bayedieng/close-ifdef ivarflakstad 2024-01-11 22:14:38 +01:00
• 85e5680277 remove metal version check Baye Dieng 2024-01-11 21:02:03 +00:00
• 1327419776 close ifdef Baye Dieng 2024-01-11 17:14:12 +00:00
• 402349d120 feat(bf16): add cast support + tests for cast + bin ops (#1524) Kyle McCarthy 2024-01-11 08:49:13 -06:00
• 9f0c99f0c1 Seperate benchmarks by enabled features (#1538) ivarflakstad 2024-01-11 15:35:38 +01:00
• 0fc95c9f0c Add a dequantize command to tensor-tools. (#1565) Laurent Mazare 2024-01-11 11:21:01 +01:00
• 2480c5dbdd Add RepVGG model. (#1561) Jani Monoses 2024-01-11 08:07:40 +02:00
• 63944714f2 Use candle_nn::embedding instead of local copies in a few models. (#1562) Jani Monoses 2024-01-10 22:36:27 +02:00
• d3bdd788cf Use __HAVE_BFLOAT__ to check for bfloat support instead of metal version check (#1540) ivarflakstad 2024-01-10 18:50:30 +01:00
• ae06cb74bb Add relu kernel for metal (#1488) Juarez Bochi 2024-01-10 12:27:17 -05:00
• a897fda74e Update memmap2 requirement from 0.7.1 to 0.9.3 (#1556) dependabot[bot] 2024-01-10 16:27:59 +01:00
• 1f1179913a Update gloo requirement from 0.8 to 0.11 (#1558) dependabot[bot] 2024-01-10 16:27:20 +01:00
• 6e98cf2a92 Update cudarc requirement from 0.9.14 to 0.10.0 (#1559) dependabot[bot] 2024-01-10 16:27:05 +01:00
• 2cc1247999 Update tokenizers requirement from 0.13.4 to 0.15.0 (#1555) dependabot[bot] 2024-01-10 16:26:53 +01:00
• cdbdb4af9c Update yew-agent requirement from 0.2.0 to 0.3.0 dependabot/cargo/yew-agent-0.3.0 dependabot[bot] 2024-01-10 14:14:03 +00:00
• edf3fcd1c4 fix: deprecated option field (open-pull-requests-limit-per-dependency) (#1554) darker 2024-01-10 15:12:46 +01:00
• 53e4755015 feat: add dependabot to the project (#1553) darker 2024-01-10 14:57:20 +01:00
• 87efb5d8eb Updated feature separated benchmarks Ivar Flakstad 2024-01-09 19:04:31 +01:00
• ad181f9cdc Merge branch 'ivarflakstad/seperate-benchmarks-by-feature' into ivarflakstad/metal-prng Ivar Flakstad 2024-01-09 18:55:40 +01:00
• 45936a18f8 Update with feature separated benchmarks Ivar Flakstad 2024-01-09 18:54:48 +01:00
• 4462198bc1 Merge branch 'ivarflakstad/seperate-benchmarks-by-feature' into ivarflakstad/metal-fill Ivar Flakstad 2024-01-09 18:48:51 +01:00
• 88945f2c22 Improve benchmarks layout Ivar Flakstad 2024-01-09 18:31:28 +01:00
• 12b2a337f3 Handle start-offset when loading a tensor from a pickle file. (#1546) Laurent Mazare 2024-01-08 09:20:48 +01:00
• fb05af4c42 Avoid some unnecessary returns. Laurent 2024-01-08 07:19:59 +01:00
• ad075a5f7e Remove allow pragma Ivar Flakstad 2024-01-08 06:48:33 +01:00
• c2261d0222 Merge. bug_q4k Laurent 2024-01-07 20:27:33 +01:00
• 0eb90ed783 Simpler repro for the neon optimization issue + bugfix (#1544) Laurent Mazare 2024-01-07 20:21:49 +01:00
• 89b5a06858 Use bindgen-cuda for the custom-kernel example. (#1536) Laurent Mazare 2024-01-07 17:18:46 +01:00
• 3f04a79ada Use cfg to seperate benchmark results based on features Ivar Flakstad 2024-01-07 14:40:15 +01:00
• 30313c3081 Moving to a proper build crate bindgen_cuda. (#1531) Nicolas Patry 2024-01-07 12:29:24 +01:00
• e72d52b1a2 Unpin more of the workplace relative dependencies. (#1535) Laurent Mazare 2024-01-07 12:26:20 +01:00
• b4cb982e49 Simplifying our internal cargo dependencies. (#1529) Nicolas Patry 2024-01-07 12:04:14 +01:00
• 6ebe043273 Merge branch 'main' into ivarflakstad/metal-prng Ivar Flakstad 2024-01-07 11:52:03 +01:00
• 6bf52b9fdf Gaussian normal distribution of PRNG via Box-Muller transform Ivar Flakstad 2024-01-05 21:18:12 +01:00
• 06d186355b Change more consitently the test. Nicolas Patry 2024-01-06 15:20:55 +01:00
• 2bbd544832 Non random for better quantization quality Nicolas Patry 2024-01-06 15:16:01 +01:00
• 84250bf52f fix index_pos bug when kv cache is disabled. (#1517) optman 2024-01-06 18:43:01 +08:00
• 9cd0cc1f65 Ignore rotary for mistral. tmp_no_rotary Nicolas Patry 2024-01-05 21:55:13 +01:00
• 12fc4af8f2 Ignore rotary. Nicolas Patry 2024-01-05 21:38:39 +01:00
• 9130b6c4b6 Removing the fences speeds everything up and *is* correct this time... Nicolas Patry 2024-01-05 19:26:30 +01:00
• 8d1a57c9a0 chore: update flash attention kernels (#1518) OlivierDehaene 2024-01-05 18:28:55 +01:00
• 7b4389099a Fix the rebase. Nicolas Patry 2024-01-05 14:31:39 +01:00
• 6f8584091e Cleanup. Nicolas Patry 2024-01-05 14:28:08 +01:00
• f97fcd4712 Metal quantized modifications proposal. Nicolas Patry 2023-11-18 14:49:30 +01:00
• 504d0b9ac7 Potential bug on q4k. Nicolas Patry 2024-01-05 14:13:22 +01:00
• 955e63c803 Implement hybrid Tausworthe + LCG psuedo random number generator in metal Ivar Flakstad 2024-01-05 13:27:59 +01:00
• 3a7304cb0d add link to gpt-from-scratch-rs (#1525) Jeroen Vlek 2024-01-05 11:59:46 +01:00
• fa3ea98ba9 Adding bfloat16 support for the cast kernels. (#1520) Nicolas Patry 2024-01-04 12:12:56 +01:00
• e8e24f1284 Follow crate conventions Ivar Flakstad 2024-01-01 20:37:56 +01:00
• 6eb44d1bce Added fill bench Ivar Flakstad 2024-01-01 20:22:44 +01:00
• 135ae5f3eb Simplify the one-hot implementation, support arbitrary rank. (#1514) Laurent Mazare 2024-01-01 11:40:17 +01:00
• 41614b4a9b Add one-hot/cold encoding (#1489) Ryan Tate 2024-01-01 02:18:40 -08:00
• 03ce8caf40 Format properly the Stable Diffusion example run with params (#1511) stano 2024-01-01 12:13:35 +02:00
• b0fe5e4453 Do not implement Module for BatchNorm. (#1513) Laurent Mazare 2024-01-01 10:13:13 +01:00
• 1fb2dd905c Add support for tiny-llama-1.1b. (#1512) Laurent Mazare 2023-12-31 12:18:25 +01:00
• a0facd0e67 Small tweaks to batch-norm. (#1505) Laurent Mazare 2023-12-30 17:06:07 +01:00
• 4290b81244 [Breaking] Add training to batchnorm with exponential moving average (#1504) nkoppel 2023-12-30 15:42:08 +00:00
• 51e577a682 Add Policy Gradient to Reinforcement Learning examples (#1500) s-casci 2023-12-30 09:01:29 +01:00
• 0a245e6fa4 Metal: support unary abs (#1503) Gonzalo 2023-12-29 20:00:12 -03:00
• 87d7f81b43 Metal: more u8/u32 (#1502) Gonzalo 2023-12-29 19:56:21 -03:00
• 4373534d59 Metal: i64 basic support (#1495) Gonzalo 2023-12-29 15:42:50 -03:00
• 7fc26764b6 Implement generic fill. u8 uses speedy blit encoder Ivar Flakstad 2023-12-29 16:02:29 +01:00
• f4a2787217 Merge pull request #1498 from huggingface/debugging_windows_ci Nicolas Patry 2023-12-29 12:33:50 +01:00
• 0a29d2e9b8 Add fill kernel handler Ivar Flakstad 2023-12-29 12:27:12 +01:00
• 488e02a3f6 Merge pull request #1496 from bayedieng/unary Nicolas Patry 2023-12-29 12:20:52 +01:00
• adc95ca2bf Ignore skipped. Nicolas Patry 2023-12-29 12:15:57 +01:00
• 4907c63ea1 Ignore stop on remote forks. Nicolas Patry 2023-12-29 12:12:10 +01:00
• d76ac20e0e Fix. Nicolas Patry 2023-12-29 12:06:38 +01:00
• f5c98f22c7 Merge pull request #1491 from mimiquate/metal-errors Nicolas Patry 2023-12-29 12:03:40 +01:00
• fd9bf3bcdd remove stray # Ivar Flakstad 2023-12-29 11:39:49 +01:00
• 90c74e199c Add metal fill kernel Ivar Flakstad 2023-12-29 11:38:13 +01:00
• 5b12fbb143 Trying to fix flakyness by making hub_2 and hub_3 serial tests (potential issue on mingw with mmap). Nicolas Patry 2023-12-29 11:13:33 +01:00