Commit Graph

Select branches

Hide Pull Requests

8bit-model

8bit_backward

8bit_blocks

8bit_model_inference

CI

add-sst2-example

amd-gpus

beamsearch

beat-docker-into-submission

bnb-0-41-1

bootstrap-peers

borzunov-patch-1

borzunov-patch-2

bump

cache

client

client-attempt2

client-convenience

dbaranchuk-patch-1

debug-leak

declare_adapters

deep-prompt-tuning

deep_prompt_inference

demo-1

diff

diff-compression

distributed-deep-ptune

download_8bit_weights

efficient-forward-backward

empty-weights

enable-rebalancing

examples_fix_hivemind

extract-module-container

facelift

fault-tolerant-inference

fix-auth-token

fix-branch-name

fix-cache

fix-ci

fix-convert-8bit

fix-distr-seq-cls

fix-docker

fix-inference-retry

fix-joining-announce

fix-master-ci

fix-nf4-and-dtypes

fix-pb2

fix-protobuf

fix-ptune

fix-readme

fix-rebalancing-issues

fix-requirements

fix-seq-backward-recovery

fix-too-many-open-files

fix3

forward-backward-timeouts

forward_backward

forward_kwargs

friendly-timeout-errors

generation

generation-inference

get_sequence

hivemind-1.1.4

hivemind-dht-fork-process

hotfix_bnb

inference_chain

instruction-readability-style

investigate-segfault

justheuristic-patch-1

justheuristic-patch-2

justheuristic-patch-3

justheuristic-patch-4

justheuristic-patch-5

lm_head

load-balancing

lora_from_hub

lru

main

main_fix

measure-throughput

measurements

memory_savings

mockup

multiple-experts

no-cpufeature

no_qkv_merge

optimize_seq

partial_rollback

payload-size

peft_update

petals-readme-title

pip-installable

pip-installable-v2

priority-tasks

processing_attention

prompt-inference

prompt-tuning

ptune-example-personachat

ptune-wip

pytest-verbose

qkv_merge

readme-clarifications

readme-release

remove-remote-block

rename-test-model

repetition-penalty

rpc

rtfd

sequence

server-dtypes

server-increase-startup-timeout

server-logging

server-timeouts

standardize

support-backend-dtypes

test-push

test_main

test_opt_serving

upd-deps

update-bullet-points

update-hivemind

update-model

update-readme-disclaimers-faq

update-readme-pics

update_example_1

vectorized_beam_search

versions

warn-about-6b-instructions

wip_triton

yozh-dev-branch

#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

#148

#149

#150

#151

#152

#153

#154

#155

#156

#157

#159

#160

#161

#162

#163

#165

#166

#168

#169

#17

#170

#171

#172

#173

#175

#176

#177

#179

#18

#180

#181

#182

#183

#184

#185

#186

#187

#188

#189

#19

#190

#191

#194

#195

#196

#197

#198

#199

#20

#200

#204

#205

#206

#209

#21

#210

#211

#212

#213

#214

#215

#217

#218

#219

#22

#221

#224

#225

#227

#229

#23

#230

#231

#232

#234

#235

#24

#243

#244

#245

#247

#248

#249

#25

#251

#252

#253

#257

#259

#26

#260

#263

#264

#265

#266

#267

#27

#273

#273

#275

#276

#277

#278

#28

#284

#285

#286

#287

#29

#290

#292

#297

#298

#299

#30

#300

#301

#302

#304

#305

#306

#307

#309

#31

#310

#311

#312

#313

#314

#315

#316

#319

#32

#323

#324

#325

#329

#33

#330

#331

#332

#333

#334

#335

#336

#337

#339

#34

#340

#341

#342

#343

#344

#345

#346

#348

#349

#35

#350

#351

#352

#353

#354

#355

#356

#357

#358

#36

#360

#362

#364

#365

#369

#37

#370

#371

#373

#374

#377

#378

#379

#38

#380

#383

#384

#385

#39

#390

#391

#392

#393

#396

#397

#399

#40

#402

#403

#404

#406

#407

#409

#41

#410

#411

#418

#42

#422

#423

#424

#428

#43

#430

#431

#434

#435

#436

#437

#438

#438

#44

#440

#441

#442

#443

#445

#448

#45

#451

#452

#454

#456

#458

#459

#46

#461

#462

#463

#464

#467

#467

#47

#470

#471

#472

#473

#474

#475

#476

#477

#478

#479

#48

#480

#482

#484

#485

#486

#487

#489

#49

#490

#491

#493

#493

#496

#497

#498

#498

#499

#50

#500

#501

#502

#504

#505

#505

#506

#506

#510

#513

#516

#517

#52

#520

#523

#523

#525

#53

#530

#531

#535

#537

#538

#539

#54

#543

#544

#544

#545

#545

#547

#547

#55

#552

#553

#554

#555

#555

#557

#557

#558

#559

#560

#560

#563

#567

#57

#570

#572

#574

#577

#579

#58

#580

#59

#60

#61

#62

#63

#64

#65

#66

#69

#70

#71

#72

#73

#74

#75

#76

#77

#80

#81

#82

#83

#84

#85

#86

#87

#88

#89

#9

#90

#91

#92

#93

#94

#95

#96

#97

#98

#99

v1.0.0

v1.1.0

v1.1.1

v1.1.2

v1.1.3

v1.1.4

v1.1.5

v2.0.0.post1

v2.0.0.post2

v2.0.0.post3

v2.0.1

v2.0.1.post1

v2.0.1.post2

v2.1.0

v2.2.0

Mono Color

• e1e478d45c
  Merge 4dcb735732 into e268c99a6b elsolo5000-2 2024-05-06 02:47:40 -0400
• 5744205357 added setup.sh and added .env.example mike dupont 2024-04-29 20:11:40 +0000
• a13e0986f5
  Merge pull request #1 from jmikedupont2/feature/dht1 Richard Bakobiibizo 2024-04-29 11:26:26 -0700
• db5cb42d40 update config mike dupont 2024-04-29 14:21:31 -0400
• e268c99a6b
  Restrict PyTorch version to <2.3.0 to resolve import error (#577) main Priyanshupareek 2024-04-27 19:05:07 +0530
• 88e1d6a990
  Update setup.cfg Priyanshupareek 2024-04-27 18:06:34 +0530
• 0d437de2cf
  Pin PyTorch version to 2.2.2 to resolve import error Priyanshupareek 2024-04-25 16:31:06 +0530
• dd4a171acd
  Merge 08b83d27c9 into 30f522d1a0 Romech 2024-04-19 15:07:09 +0800
• 088ba3f74b
  Merge 26d4cd855d into 30f522d1a0 Denis Mazur 2024-04-19 15:06:51 +0800
• 1644e89385 reformat black mike dupont 2024-04-17 12:56:48 -0400
• 3365e2efbf Merge branch 'feature/docker-compose' mike dupont 2024-04-17 12:50:40 -0400
• 6124622667 mixtral working mike dupont 2024-04-17 12:46:20 -0400
• c98b5328cb docker changes mike dupont 2024-04-17 12:35:10 -0400
• be69f3117f grok mike dupont 2024-04-16 14:58:27 -0400
• 661545f0ff tiny mixtral running locally mike dupont 2024-04-16 14:05:02 -0400
• c76e447ac7 infrastructure j mike dupont 2024-04-15 20:05:36 +0000
• 30f522d1a0
  Fix dummy cache allocation (#574) Artem Chumachenko 2024-04-16 19:25:29 +0200
• 1222e172ef github actions and docker compose Ubuntu 2024-03-28 19:14:24 +0000
• 0fda7da816 pip freeze mike dupont 2024-04-15 16:32:49 -0400
• 2a522d01f3 update j mike dupont 2024-04-15 20:05:36 +0000
• 0ca54a5e76 Rechain reloc Artem Chumachenko 2024-04-11 11:41:16 +0200
• e5dddfe0b6 Try mps device selecting Artem Chumachenko 2024-04-11 11:37:27 +0200
• f02bd578b7 Fix dummy cache allocation Artem Chumachenko 2024-04-11 10:54:32 +0200
• 2d3b63ed15 first docker compose mike dupont 2024-04-10 13:58:28 -0400
• 2325875186 moving to my org mike dupont 2024-04-10 11:20:42 -0400
• d6f4f80f3f
  Fix Mixtral-related issues (#570) Artem Chumachenko 2024-04-10 13:49:50 +0200
• 5ca2a031f5 Comments Artem Chumachenko 2024-04-10 10:48:44 +0200
• 63a421bad9 Add llama to non-bs mix Artem Chumachenko 2024-04-10 10:43:46 +0200
• e3539c0759 Comments Artem Chumachenko 2024-04-10 10:34:48 +0200
• 6a1596b633
  Update tests/test_full_model.py Artem Chumachenko 2024-04-10 10:32:04 +0200
• 1b4bb1a743 Another fix Artem Chumachenko 2024-04-10 07:34:10 +0200
• 16d97fcbce Fix benchmarks Artem Chumachenko 2024-04-10 07:23:18 +0200
• a447cbe16d Add assert about BS Artem Chumachenko 2024-04-10 07:12:11 +0200
• 5f91793f8c Skip BS for mixtral for now Artem Chumachenko 2024-04-09 15:26:49 +0200
• ba271dc626 Fix get_model_block Artem Chumachenko 2024-04-08 19:41:59 +0200
• 2ca531623c Return compatibility with tests Artem Chumachenko 2024-04-08 19:40:03 +0200
• 0f498814be Fix cache again Artem Chumachenko 2024-04-08 19:34:47 +0200
• 46e29b230e Fix cache in tests Artem Chumachenko 2024-04-08 19:27:10 +0200
• d41ff56047 Fix type Artem Chumachenko 2024-04-08 19:13:00 +0200
• db3087aee9 Style Artem Chumachenko 2024-04-08 19:02:47 +0200
• 9eb7928bef Add mixtral in tests Artem Chumachenko 2024-04-08 19:00:56 +0200
• 204855c751 fix cache and throughput Artem Chumachenko 2024-04-08 18:59:13 +0200
• c6dd015ea3 petals inference John Doe 2024-04-08 16:17:30 +0000
• f06cfd2b97 fix imports Artem Chumachenko 2024-04-08 18:08:57 +0200
• aecf074f25 fix block init Artem Chumachenko 2024-04-08 18:04:50 +0200
• 5b7e7c7375 update mike dupont 2024-04-08 11:48:52 -0400
• dfcdaca2ac run Ubuntu 2024-03-28 19:14:24 +0000
• 84dd3a1a5d
  Merge b945e388e5 into d2fcbbc72e Alexander Borzunov 2024-04-08 10:22:01 +0800
• c44c6cba92 working as root John Doe 2024-03-30 15:48:57 +0000
• 998cb34722 adding steps John Doe 2024-03-30 14:56:26 +0000
• afe06e1757 update Ubuntu 2024-03-28 19:34:10 +0000
• 80443ec10a run Ubuntu 2024-03-28 19:14:24 +0000
• 03e49d93f2 Fix p2p pushing in rpc_inference (by @miaoqijun ) , support transformers 4.38.2 (#563) justheuristic 2024-03-18 00:11:47 +0300
• b638b046ee Clean disk space in push-docker-image.yaml (#558) justheuristic 2024-03-02 20:25:03 +0300
• f7e13c40db Bump transformers and accelerate versions (#554) Denis Mazur 2024-02-15 15:24:37 +0300
• b2b3f974b2 Bump version for inference diagnostics (#543) justheuristic 2023-11-16 06:12:30 +0300
• 29363912c4 Optimize LLaMA for inference (#513) Max Ryabinin 2023-11-14 18:14:19 +0100
• 83c7b5639f Hotfix: require peft version 0.5.0 (#539) justheuristic 2023-11-07 19:05:54 +0300
• 3e6c09ffd7 Hotfix: set transformers version <=4.34 temporarily (#538) justheuristic 2023-11-07 18:19:19 +0300
• d1ec0076fc Fix beam search in GPU clients (#531) Alexander Borzunov 2023-10-23 20:13:13 +0400
• 376de004fe Improve default arguments for clients and servers (#530) Alexander Borzunov 2023-10-23 05:26:40 +0600
• 90780d6da2 Add position_ids argument to DistributedFalconModel (#525) Max Ryabinin 2023-10-08 22:09:46 +0300
• 5b09563e84 Update README.md (#520) Alexander Borzunov 2023-09-22 06:16:32 +0400
• 96d5cee0fe Fix file locks in NFS-mounted directories (#517) FYY 2023-09-19 20:01:23 -0400
• 9157e13b94 Store (start_block, end_block) in each DHT record for reliability (#510) Alexander Borzunov 2023-09-15 23:53:57 +0400
• 9b83ef6b1d Bump version to 2.2.0 (#502) Alexander Borzunov 2023-09-06 19:43:30 +0400
• edcd8ff56f Optimize the Falcon block for inference (#500) Max Ryabinin 2023-09-04 14:38:32 +0200
• 5b5285fc67 Fix prompt tuning after #464 (#501) Alexander Borzunov 2023-09-04 12:25:29 +0400
• 5f36029534 Add Falcon support (#499) Alexander Borzunov 2023-09-04 01:45:37 +0400
• b3952e16ee Force use_cache=True in config only (#497) Alexander Borzunov 2023-09-03 01:16:00 +0400
• 85c0db6883 Force use_cache=True (#496) Alexander Borzunov 2023-09-02 22:57:18 +0400
• 6065bc7140 Create model index in DHT (#491) Alexander Borzunov 2023-08-31 10:31:03 +0400
• e3e9cbe358 Replace dots in repo names when building DHT prefixes (#489) Alexander Borzunov 2023-08-30 23:31:39 +0400
• ad7cab39d6 Fix race condition in MemoryCache (#487) Alexander Borzunov 2023-08-30 14:13:43 +0400
• 0034745f13 Wait for DHT storing state OFFLINE on shutdown (#486) Alexander Borzunov 2023-08-30 07:48:11 +0400
• f68cced72a Fix `.generate(input_ids=...)` (#485) Alexander Borzunov 2023-08-30 06:59:33 +0400
• 6205344c3d Remove no-op process in PrioritizedTaskPool (#484) Alexander Borzunov 2023-08-30 06:07:04 +0400
• 20d04b73a8 Support macOS (#477) Alexander Borzunov 2023-08-29 07:49:27 +0400
• f70d2a550c Refactor readme (#482) Alexander Borzunov 2023-08-28 19:09:13 +0400
• c1bec34dd7 Rewrite MemoryCache alloc_timeout logic (#434) justheuristic 2023-08-28 16:01:50 +0300
• 44f4498883 Fix requiring transformers>=4.32.0 (#480) Alexander Borzunov 2023-08-26 05:32:16 +0400
• 1498e2936e Require transformers>=4.32.0 (#479) Alexander Borzunov 2023-08-25 01:37:30 +0400
• f4ae9dcffc Don't install cpufeature on non-x86_64 machines (#478) Alexander Borzunov 2023-08-24 19:57:15 +0400
• fe64dfcbf5 Bump version to 2.1.0 (#474) Alexander Borzunov 2023-08-24 19:42:19 +0400
• 210ac116d7 Hide excess key message (#476) Alexander Borzunov 2023-08-24 00:41:40 +0400
• 5eea7f04ab Update peft to 0.5.0 version (#475) Artem Chumachenko 2023-08-23 20:21:28 +0400
• 76b7e0248d Support loading weights from Safetensors on server (#473) Alexander Borzunov 2023-08-23 01:43:29 +0400
• da6e1e8084 Change transformers version assert (#472) justheuristic 2023-08-22 20:53:14 +0300
• dcdc7f84e9 Support transformers 4.32.x (#471) justheuristic 2023-08-22 20:10:29 +0300
• 005033c995 Temporarily require peft<0.5.0, transformers<4.32.0 (#470) justheuristic 2023-08-22 19:45:37 +0300
• d2c68d92e7
  Merge 7fdbc84b95 into d2fcbbc72e Daniel Ahern 2024-03-30 13:49:52 +0100
• 94445cd0c7
  Merge 3f66c3615a into d2fcbbc72e Artem Chumachenko 2024-03-29 14:26:47 +0300
• 3f66c3615a Remove unnesc todo peft_update Artem Chumachenko 2024-03-29 12:26:41 +0100
• 96cf244fae
  Update comments Artem Chumachenko 2024-03-29 12:23:51 +0100
• b143055547 style Artem Chumachenko 2024-03-05 13:45:41 +0400
• e90612221b Fix versions Artem Chumachenko 2024-03-05 13:45:16 +0400
• 7d9afb0fb4 Fix trainability Artem Chumachenko 2024-03-05 13:08:06 +0400
• a93221a9f3 Fix inference without adapter Artem Chumachenko 2024-03-04 13:48:33 +0400
• cf4f80a020 lib number Artem Chumachenko 2024-02-27 16:53:59 +0400
• 83c95518d9 Make fixes Artem Chumachenko 2024-02-27 16:50:14 +0400