Commit Graph

Select branches

Hide Pull Requests

abetlen/bump-version-0.3.18

abetlen/fix-cuda-real-arch

abetlen/fix-hf-download-checks

abetlen/fix-linux-cpu-wheel-musl

abetlen/fix-macos-runner-label

abetlen/setup-ruff

abetlen/update-llama-cpp-bindings

add-paligemma-support

batch-processing

binary-wheels

dependabot/github_actions/conda-incubator/setup-miniconda-3.1.1

dependabot/github_actions/pypa/cibuildwheel-2.23.2

dependabot/pip/starlette-context-gte-0.3.6-and-lt-0.5

dev-add-rpc

docker

expose-libggml

fix-embeddings-for-non-embedding-models

fix-windows-import-error

generic-vlm-chat-format

main

patch-1

patch-3

remove-unwanted-bos

update-sampling-api

#10

#1002

#1005

#1007

#1010

#1011

#1012

#1015

#1019

#1021

#1023

#1028

#1037

#1050

#1052

#1058

#1059

#1067

#1067

#1068

#1078

#108

#1080

#1080

#1086

#1087

#1088

#1090

#1092

#1093

#1106

#1106

#111

#1110

#1115

#1116

#1120

#1122

#1131

#1136

#1147

#1156

#1157

#1160

#1160

#1170

#1170

#1172

#1175

#1176

#1179

#118

#1184

#1186

#1187

#1188

#119

#1193

#1194

#1205

#1206

#1209

#1209

#1210

#1212

#1212

#1214

#1222

#1230

#1232

#1244

#1246

#1247

#1248

#125

#1257

#126

#1263

#1264

#1272

#1273

#1281

#1281

#1282

#1289

#1295

#1296

#130

#1307

#1311

#1317

#1330

#1331

#1331

#1333

#1345

#1347

#135

#1350

#1351

#1351

#1353

#1364

#137

#1370

#1371

#1374

#1374

#1375

#1380

#1382

#1382

#1383

#1383

#1385

#1386

#1387

#1388

#139

#1390

#1391

#1392

#1396

#1397

#1398

#1399

#140

#1400

#1401

#1407

#1407

#1408

#1409

#1410

#1411

#1412

#1413

#1415

#1416

#1419

#1424

#1426

#1427

#1427

#1430

#1432

#1433

#1434

#1439

#144

#144

#1440

#1440

#1441

#1444

#1448

#1449

#1453

#1457

#1459

#146

#146

#1462

#1465

#1471

#1472

#1476

#1477

#1486

#1486

#1492

#1493

#1497

#15

#1503

#1503

#1509

#1509

#1513

#1514

#1515

#1515

#1516

#1522

#1525

#1526

#1527

#153

#1530

#1539

#154

#1544

#1550

#1550

#1551

#1552

#1552

#156

#1568

#1569

#157

#1576

#1583

#1583

#1585

#1589

#1590

#1594

#1596

#1597

#160

#1605

#1605

#161

#1613

#1613

#162

#1626

#163

#1630

#1632

#1633

#1634

#1635

#1637

#164

#1649

#165

#1651

#1651

#1653

#1656

#1657

#1658

#1659

#1667

#1668

#1673

#1677

#1677

#1679

#168

#1680

#1704

#1716

#1716

#1718

#1718

#172

#172

#1721

#173

#1738

#1739

#1739

#1741

#1742

#1743

#1750

#1751

#1758

#1758

#176

#176

#1761

#177

#1775

#1776

#1776

#1777

#1777

#178

#1782

#1782

#1783

#1786

#1786

#1788

#1790

#1791

#1791

#1793

#1795

#1796

#1798

#1800

#1800

#1802

#1807

#1817

#1817

#1819

#1820

#1820

#1821

#1825

#1825

#1833

#1834

#1834

#1838

#1842

#1842

#1843

#1843

#1844

#1845

#1858

#1862

#1864

#1864

#1867

#1867

#1871

#1877

#1877

#1878

#1878

#1879

#1884

#1884

#1887

#1887

#189

#1894

#1898

#1899

#1899

#190

#1901

#191

#1911

#1911

#1912

#1959

#1961

#1961

#1966

#1971

#1971

#1973

#1974

#1978

#198

#198

#1980

#1981

#1981

#1989

#1989

#1991

#1991

#2007

#2007

#2009

#2015

#2015

#2018

#2018

#2025

#2025

#2027

#203

#2030

#2034

#2034

#2039

#2039

#2040

#2041

#2041

#2042

#2042

#2044

#2044

#2046

#2049

#2056

#2056

#2058

#2058

#2059

#2059

#2066

#2066

#2071

#2071

#2072

#2072

#2077

#2082

#2082

#2083

#2083

#2085

#2085

#2088

#2088

#2099

#2099

#2100

#2102

#2102

#2108

#2108

#2109

#2109

#2112

#212

#2120

#2120

#2121

#2121

#2128

#2128

#2129

#2129

#2131

#2131

#2132

#2133

#2134

#2134

#2139

#214

#2141

#2141

#2143

#2147

#2147

#2148

#2149

#215

#2150

#2151

#2152

#2153

#2154

#2155

#2156

#2157

#2158

#2160

#2161

#2162

#2164

#2164

#2165

#2165

#217

#225

#235

#240

#246

#248

#249

#251

#252

#258

#262

#263

#264

#265

#270

#271

#274

#277

#28

#289

#29

#292

#293

#294

#295

#296

#297

#309

#310

#322

#323

#324

#325

#326

#328

#329

#329

#350

#351

#359

#360

#365

#366

#367

#368

#370

#376

#385

#390

#392

#402

#405

#41

#414

#414

#415

#42

#420

#429

#430

#431

#432

#435

#436

#442

#443

#444

#452

#453

#456

#460

#466

#481

#485

#486

#498

#499

#50

#501

#505

#505

#508

#511

#516

#517

#517

#521

#522

#523

#525

#530

#531

#532

#536

#540

#540

#548

#549

#55

#550

#551

#556

#564

#565

#567

#572

#573

#575

#575

#577

#583

#584

#594

#594

#598

#600

#604

#61

#610

#611

#612

#621

#624

#624

#625

#63

#631

#631

#633

#64

#644

#647

#648

#667

#668

#669

#670

#671

#678

#678

#680

#682

#684

#688

#690

#691

#692

#694

#694

#703

#704

#705

#709

#709

#711

#713

#716

#716

#73

#730

#733

#733

#748

#752

#752

#76

#767

#768

#772

#778

#781

#783

#784

#790

#795

#798

#799

#803

#808

#809

#820

#821

#824

#824

#826

#83

#834

#835

#842

#843

#843

#846

#848

#849

#850

#851

#854

#855

#864

#868

#868

#869

#87

#875

#892

#913

#913

#920

#921

#922

#922

#925

#927

#93

#930

#931

#934

#936

#937

#938

#940

#947

#951

#951

#952

#955

#955

#957

#958

#961

#962

#962

#967

#98

#986

#991

#993

#993

#994

#996

v0.1.29

v0.1.30

v0.1.31

v0.1.32

v0.1.33

v0.1.34

v0.1.35

v0.1.36

v0.1.37

v0.1.38

v0.1.39

v0.1.40

v0.1.41

v0.1.42

v0.1.43

v0.1.44

v0.1.45

v0.1.46

v0.1.47

v0.1.48

v0.1.49

v0.1.50

v0.1.51

v0.1.52

v0.1.53

v0.1.54

v0.1.55

v0.1.56

v0.1.57

v0.1.59

v0.1.60

v0.1.61

v0.1.62

v0.1.63

v0.1.64

v0.1.65

v0.1.66

v0.1.67

v0.1.68

v0.1.69

v0.1.70

v0.1.71

v0.1.72

v0.1.73

v0.1.74

v0.1.75

v0.1.76

v0.1.77

v0.1.78

v0.1.79

v0.1.80

v0.1.81

v0.1.82

v0.1.83

v0.1.84

v0.1.85

v0.2.0

v0.2.1

v0.2.10

v0.2.11

v0.2.12

v0.2.13

v0.2.14

v0.2.15

v0.2.16

v0.2.17

v0.2.18

v0.2.19

v0.2.2

v0.2.20

v0.2.21

v0.2.22

v0.2.23

v0.2.24

v0.2.25

v0.2.26

v0.2.27

v0.2.28

v0.2.29

v0.2.3

v0.2.30

v0.2.31

v0.2.32

v0.2.33

v0.2.34

v0.2.35

v0.2.36

v0.2.37

v0.2.38

v0.2.39

v0.2.4

v0.2.40

v0.2.41

v0.2.42

v0.2.43

v0.2.44

v0.2.45

v0.2.46

v0.2.47

v0.2.48

v0.2.49

v0.2.5

v0.2.50

v0.2.51

v0.2.52

v0.2.53

v0.2.54

v0.2.55

v0.2.56

v0.2.57

v0.2.58

v0.2.59

v0.2.59-cu121

v0.2.59-cu122

v0.2.59-cu123

v0.2.59-metal

v0.2.6

v0.2.60

v0.2.60-cu121

v0.2.60-cu122

v0.2.60-cu123

v0.2.60-metal

v0.2.61

v0.2.61-cu121

v0.2.61-cu122

v0.2.61-cu123

v0.2.61-metal

v0.2.62

v0.2.62-cu121

v0.2.62-cu122

v0.2.62-cu123

v0.2.62-metal

v0.2.63

v0.2.63-cu121

v0.2.63-cu122

v0.2.63-cu123

v0.2.63-metal

v0.2.64

v0.2.64-cu121

v0.2.64-cu122

v0.2.64-cu123

v0.2.64-metal

v0.2.65

v0.2.65-cu121

v0.2.65-cu122

v0.2.65-cu123

v0.2.65-metal

v0.2.66

v0.2.66-cu121

v0.2.66-cu122

v0.2.66-cu123

v0.2.66-cu124

v0.2.66-metal

v0.2.67

v0.2.67-cu121

v0.2.67-cu122

v0.2.67-cu123

v0.2.67-cu124

v0.2.67-metal

v0.2.68

v0.2.68-cu121

v0.2.68-cu122

v0.2.68-cu123

v0.2.68-cu124

v0.2.68-metal

v0.2.69

v0.2.69-cu121

v0.2.69-cu122

v0.2.69-cu123

v0.2.69-cu124

v0.2.69-metal

v0.2.7

v0.2.70

v0.2.70-cu121

v0.2.70-cu122

v0.2.70-cu123

v0.2.70-cu124

v0.2.70-metal

v0.2.71

v0.2.71-cu121

v0.2.71-cu122

v0.2.71-cu123

v0.2.71-cu124

v0.2.71-metal

v0.2.72

v0.2.72-cu121

v0.2.72-cu122

v0.2.72-cu123

v0.2.72-cu124

v0.2.72-metal

v0.2.73

v0.2.73-cu121

v0.2.73-cu122

v0.2.73-cu123

v0.2.73-cu124

v0.2.73-metal

v0.2.74

v0.2.74-cu121

v0.2.74-cu122

v0.2.74-cu123

v0.2.74-cu124

v0.2.74-metal

v0.2.75

v0.2.75-cu121

v0.2.75-cu122

v0.2.75-cu123

v0.2.75-cu124

v0.2.75-metal

v0.2.76

v0.2.76-cu121

v0.2.76-cu122

v0.2.76-cu123

v0.2.76-cu124

v0.2.76-metal

v0.2.77

v0.2.77-cu121

v0.2.77-cu122

v0.2.77-cu123

v0.2.77-cu124

v0.2.77-metal

v0.2.78

v0.2.78-metal

v0.2.79

v0.2.79-metal

v0.2.8

v0.2.80

v0.2.80-metal

v0.2.81

v0.2.81-cu121

v0.2.81-cu122

v0.2.81-cu123

v0.2.81-cu124

v0.2.81-metal

v0.2.82

v0.2.82-cu121

v0.2.82-cu122

v0.2.82-cu123

v0.2.82-cu124

v0.2.82-metal

v0.2.83

v0.2.83-cu121

v0.2.83-cu122

v0.2.83-cu123

v0.2.83-cu124

v0.2.83-metal

v0.2.84

v0.2.84-cu121

v0.2.84-cu122

v0.2.84-cu123

v0.2.84-cu124

v0.2.84-metal

v0.2.85

v0.2.85-cu121

v0.2.85-cu122

v0.2.85-cu123

v0.2.85-cu124

v0.2.85-metal

v0.2.86

v0.2.86-cu121

v0.2.86-cu122

v0.2.86-cu123

v0.2.86-cu124

v0.2.86-metal

v0.2.87

v0.2.87-cu121

v0.2.87-cu122

v0.2.87-cu123

v0.2.87-cu124

v0.2.87-metal

v0.2.88

v0.2.88-cu121

v0.2.88-cu122

v0.2.88-cu123

v0.2.88-cu124

v0.2.88-metal

v0.2.89

v0.2.89-cu121

v0.2.89-cu124

v0.2.89-metal

v0.2.9

v0.2.90

v0.2.90-cu121

v0.2.90-cu122

v0.2.90-cu123

v0.2.90-cu124

v0.2.90-metal

v0.3.0

v0.3.0-metal

v0.3.1

v0.3.1-metal

v0.3.10

v0.3.11

v0.3.11-metal

v0.3.12

v0.3.12-cu121

v0.3.12-cu122

v0.3.12-cu123

v0.3.12-cu124

v0.3.12-metal

v0.3.13

v0.3.13-cu121

v0.3.13-cu122

v0.3.13-cu123

v0.3.13-cu124

v0.3.13-metal

v0.3.14

v0.3.14-cu124

v0.3.14-metal

v0.3.15

v0.3.15-cu121

v0.3.15-cu122

v0.3.15-cu123

v0.3.15-cu124

v0.3.15-metal

v0.3.16

v0.3.16-cu121

v0.3.16-cu122

v0.3.16-cu123

v0.3.16-cu124

v0.3.16-metal

v0.3.17

v0.3.17-metal

v0.3.18

v0.3.18-cu121

v0.3.18-cu122

v0.3.18-cu123

v0.3.18-cu124

v0.3.18-metal

v0.3.19

v0.3.19-cu121

v0.3.19-cu122

v0.3.19-cu123

v0.3.19-cu124

v0.3.19-metal

v0.3.2

v0.3.2-metal

v0.3.3

v0.3.4

v0.3.4-cu121

v0.3.4-cu122

v0.3.4-cu123

v0.3.4-cu124

v0.3.4-metal

v0.3.5

v0.3.5-metal

v0.3.6

v0.3.7

v0.3.8

v0.3.9

Mono Color

• 1848afebe0 Added dependencies. Maximilian-Winter 2023-05-31 22:41:35 +02:00
• 29f9c9cca3 Added both LlamaChache classes Disk and RAM. Maximilian-Winter 2023-05-31 22:33:56 +02:00
• 217d78320f Added paramterised search and d/l for Hugging Face. Updated README.md Gary Mulder 2023-05-31 16:00:31 +00:00
• 483b6ba53a Updated README.md instructions on how to use *_simple/Dockerfiles Gary Mulder 2023-05-31 15:16:32 +00:00
• 9ea7a379d3 Merge branch 'abetlen:main' into main Maximilian Winter 2023-05-31 12:55:51 +02:00
• 232880cbc6 Merge pull request #297 from gjmulder/update-issue-tmpl-llamacpp-repro Andrei 2023-05-30 14:48:14 -04:00
• 9dd8cf3472 Update bug_report.md Gary Mulder 2023-05-30 08:20:34 +01:00
• cb0bcdbbb7 Bump version v0.1.56 Andrei Betlen 2023-05-30 03:07:36 -04:00
• f4ff8a03c4 Add numpy dependency to pyproject Andrei Betlen 2023-05-30 03:06:57 -04:00
• 828f9ec015 Merge branch 'main' of github.com:abetlen/llama_cpp_python into main Andrei Betlen 2023-05-29 21:39:40 -04:00
• b1daf568e3 Update changelog Andrei Betlen 2023-05-29 21:39:19 -04:00
• 825912a3a5 Merge pull request #293 from abetlen/dependabot/pip/typing-extensions-4.6.2 Andrei 2023-05-29 21:28:27 -04:00
• f4fc126a00 Bump typing-extensions from 4.5.0 to 4.6.2 dependabot[bot] 2023-05-30 01:09:10 +00:00
• 213549787a Merge pull request #294 from abetlen/dependabot/pip/uvicorn-0.22.0 Andrei 2023-05-29 21:07:41 -04:00
• 8dfb0816df Bump uvicorn from 0.21.1 to 0.22.0 dependabot[bot] 2023-05-30 01:04:25 +00:00
• f5d136d0aa Merge pull request #295 from abetlen/dependabot/pip/mkdocs-material-9.1.15 Andrei 2023-05-29 21:02:27 -04:00
• 49fe9395a1 Merge pull request #277 from abetlen/add-numpy-support Andrei 2023-05-29 20:59:30 -04:00
• 38b918503f Bump mkdocs-material from 9.1.14 to 9.1.15 dependabot[bot] 2023-05-30 00:40:52 +00:00
• b61b016585 Merge pull request #296 from abetlen/dependabot/pip/scikit-build-0.17.5 Andrei 2023-05-29 20:39:52 -04:00
• fa79484a29 Bump scikit-build from 0.13.0 to 0.17.5 dependabot[bot] 2023-05-30 00:29:33 +00:00
• 41e2184431 Merge pull request #292 from abetlen/dependabot/pip/mkdocstrings-0.22.0 Andrei 2023-05-29 20:28:02 -04:00
• 62ac7c3761 Bump mkdocstrings from 0.21.2 to 0.22.0 dependabot[bot] 2023-05-29 21:03:33 +00:00
• 719c3eae0a Diskcache implementation for llama state. Maximilian-Winter 2023-05-28 15:56:38 +02:00
• 80066f0b80 Use async routes Andrei Betlen 2023-05-27 09:12:58 -04:00
• c2b59a5f59 Import unnused import Andrei Betlen 2023-05-26 22:59:29 -04:00
• 8f2b4456ad Format Andrei Betlen 2023-05-26 22:04:31 -04:00
• 84e313bd6e Align dtype to match c structs Andrei Betlen 2023-05-26 22:02:16 -04:00
• b0b154cfa6 Add changelog message for numpy Andrei Betlen 2023-05-26 20:26:08 -04:00
• 66bcb8d70d Merge branch 'main' into add-numpy-support Andrei Betlen 2023-05-26 20:25:03 -04:00
• 8f35bddd7e Fix stop sequence performance bug. Andrei Betlen 2023-05-26 20:23:49 -04:00
• 7fc7bc30e7 Remove usage of eval_tokens for cache check Andrei Betlen 2023-05-26 20:12:05 -04:00
• fe331ec589 Replace eval_logits and eval_tokens with numpy arrays Andrei Betlen 2023-05-26 20:03:31 -04:00
• 00ea3af51b Add makefile Andrei Betlen 2023-05-26 17:56:20 -04:00
• 447a3d249e Merge branch 'main' into setup Andrei Betlen 2023-05-26 17:53:58 -04:00
• efb763bcdc Merge branch 'main' into add-numpy-support Andrei Betlen 2023-05-26 17:37:33 -04:00
• 030fafe901 Add project changelog Andrei Betlen 2023-05-26 17:32:34 -04:00
• 878c7d363f Merge branch 'main' into add-numpy-support Andrei Betlen 2023-05-26 17:22:29 -04:00
• 6075e17cb6 Bump version v0.1.55 Andrei Betlen 2023-05-26 17:21:51 -04:00
• bd4b95da45 Reduce numpy version dependency Andrei Betlen 2023-05-26 16:38:21 -04:00
• 8eb9769f78 Add support for numpy Andrei Betlen 2023-05-26 16:12:45 -04:00
• 2adf6f3f9a Merge pull request #265 from dmahurin/fix-from-bytes-byteorder Andrei 2023-05-26 12:53:06 -04:00
• 34ad71f448 Merge pull request #274 from dmahurin/fix-missing-antiprompt Andrei 2023-05-26 12:52:34 -04:00
• d78453c045 Merge pull request #264 from dmahurin/fix-min-keep Andrei 2023-05-26 12:52:05 -04:00
• 4c1b7f7a76 Bugfix for logits_processor and stopping_criteria Andrei Betlen 2023-05-26 10:25:28 -04:00
• 0fa2ec4903 low_level_api_chat_cpp.py: Fix missing antiprompt output in chat. Don Mahurin 2023-05-26 06:35:15 -07:00
• 433a2e3e8a Add extra logits_processor and stopping_criteria Andrei Betlen 2023-05-26 03:13:24 -04:00
• 30bf8ec557 Update llama.cpp Andrei Betlen 2023-05-26 03:03:11 -04:00
• f74b90ed67 Fix streaming hang on last token when cache is on. Andrei Betlen 2023-05-26 03:03:01 -04:00
• 5be8354e11 Added tokenizer Andrei Betlen 2023-05-26 03:00:51 -04:00
• 8fa2ef1959 Format Andrei Betlen 2023-05-26 03:00:35 -04:00
• 6bd1075291 Merge branch 'Maximilian-Winter/main' into main Andrei Betlen 2023-05-26 02:56:11 -04:00
• ca01f98e09 Add LlamaTokenizer class Andrei Betlen 2023-05-25 14:11:33 -04:00
• 1d247e0f35 Add StoppingCriteria and LogitsProcessor to generate to match huggingface API Andrei Betlen 2023-05-25 14:04:54 -04:00
• c6a9659972 Merge branch 'abetlen:main' into main Maximilian Winter 2023-05-25 17:09:19 +02:00
• de8d9a810b Merge pull request #270 from gjmulder/auto-docker Andrei 2023-05-25 09:30:13 -04:00
• 0e0c9bb978 Merge branch 'auto-docker' of github.com:gjmulder/llama-cpp-python-gary into auto-docker Gary Mulder 2023-05-25 11:50:34 +00:00
• 0d2cc21202 Fixed repeated imports Gary Mulder 2023-05-25 11:50:02 +00:00
• c2585b6889 Fixed list elements typing Maximilian-Winter 2023-05-25 10:54:08 +02:00
• da463e6c8c Added types to logit processor list and stop criteria list Maximilian-Winter 2023-05-25 09:07:16 +02:00
• c05fcdf42f Fixed none value of logits processors. Maximilian-Winter 2023-05-24 22:02:06 +02:00
• 5bb780d455 Implemented logit processors and stop criteria's Maximilian-Winter 2023-05-24 21:55:44 +02:00
• fab064ded9 Remove unnecessary ffi calls Andrei Betlen 2023-05-23 17:56:21 -04:00
• ec44bdad61 Update README.md Gary Mulder 2023-05-23 20:50:39 +01:00
• ed19071ef8 Renamed and moved old Dockerfiles Gary Mulder 2023-05-23 19:38:37 +00:00
• 70f629a72f Update README.md Gary Mulder 2023-05-23 20:36:21 +01:00
• eaff7a8678 Initial commit of auto docker Gary Mulder 2023-05-23 19:26:40 +00:00
• d6a7adb17a fix "missing 1 required positional argument: 'min_keep'" Don Mahurin 2023-05-22 23:54:57 -07:00
• 327eedbfe1 fix "from_bytes() missing required argument 'byteorder'" Don Mahurin 2023-05-22 23:56:25 -07:00
• e5d596e0e9 Bump version v0.1.54 Andrei Betlen 2023-05-22 23:50:58 -04:00
• c41b1ebca7 Update llama.cpp Andrei Betlen 2023-05-22 23:50:35 -04:00
• aa3d7a6299 Merge pull request #263 from abetlen/dependabot/pip/mkdocs-material-9.1.14 Andrei 2023-05-22 23:44:51 -04:00
• 2240b949ae Bump mkdocs-material from 9.1.12 to 9.1.14 dependabot[bot] 2023-05-22 21:18:57 +00:00
• 01c79e7bf1 Merge pull request #258 from Pipboyguy/main Andrei 2023-05-22 17:17:17 -04:00
• c3e80b1714 Merge pull request #262 from abetlen/dependabot/pip/httpx-0.24.1 Andrei 2023-05-22 17:16:16 -04:00
• 8e41d724ab Bump httpx from 0.24.0 to 0.24.1 dependabot[bot] 2023-05-22 21:05:39 +00:00
• e6639e6620 Change docker build dynamic param to image instead of cuda version Marcel Coetzee 2023-05-22 10:10:14 +02:00
• 4f7a6daa25 Merge pull request #248 from localagi/main Andrei 2023-05-22 03:15:15 -04:00
• 0adb9ec37a Use model_name and index in response Andrei Betlen 2023-05-21 21:30:03 -04:00
• 922b5b2bfd Merge branch 'main' into server-embedding Andrei Betlen 2023-05-21 21:21:38 -04:00
• 2c45255a0a Bump version v0.1.53 Andrei Betlen 2023-05-21 19:24:20 -04:00
• cd102e9da1 Cache shared library function calls for static tokens Andrei Betlen 2023-05-21 19:18:56 -04:00
• b895511cca Fix penalize_nl Andrei Betlen 2023-05-21 18:38:06 -04:00
• 03e2947b03 Fix unnecessary memory allocation while sampling Andrei Betlen 2023-05-21 18:36:34 -04:00
• fafe47114c Update llama.cpp Andrei Betlen 2023-05-21 17:47:21 -04:00
• 8f49ca0287 Bump version v0.1.52 Andrei Betlen 2023-05-20 08:53:40 -04:00
• 76b1d2cd20 Change properties to functions to match token functions Andrei Betlen 2023-05-20 08:24:06 -04:00
• a7ba85834f Add n_ctx, n_vocab, and n_embd properties Andrei Betlen 2023-05-20 08:13:41 -04:00
• 0b079a658c make git module accessible anonymously Your Name 2023-05-20 02:25:59 +01:00
• e783f1c191 feat: make embedding support list of string as input Simon Chabot 2023-05-20 01:23:32 +02:00
• 01a010be52 Fix llama_cpp and Llama type signatures. Closes #221 Andrei Betlen 2023-05-19 11:59:33 -04:00
• fb57b9470b Merge branch 'main' of github.com:abetlen/llama_cpp_python into main v0.1.51 Andrei Betlen 2023-05-19 03:19:32 -04:00
• f82d85fbee Bump version Andrei Betlen 2023-05-19 03:19:27 -04:00
• c7788c85ab Add Guidance example Andrei Betlen 2023-05-19 03:16:58 -04:00
• a8cd169251 Bugfix: Stop sequences can be strings Andrei Betlen 2023-05-19 03:15:08 -04:00
• f0812c4d8c Add upgrade instructions to the README Andrei Betlen 2023-05-19 02:20:41 -04:00
• 17d4271b04 Fix logprobs for completions and implement for streaming logprobs. Andrei Betlen 2023-05-19 02:20:27 -04:00
• a634a2453b Allow first logprob token to be null to match openai api Andrei Betlen 2023-05-19 02:04:57 -04:00
• dc39cc0fa4 Use server sent events function for streaming completion Andrei Betlen 2023-05-19 02:04:30 -04:00
• 69f9d50090 Merge pull request #235 from Pipboyguy/main Andrei 2023-05-18 13:42:04 -04:00
• f0ec6e615e Stream tokens instead of text chunks Andrei Betlen 2023-05-18 11:35:59 -04:00