petals

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

894cd5d586 Merge branch 'fix-auth-token' into main justheuristic 2022-06-28 13:15:34 +0300
4d27080ccc add scripts to deploy a swarm Dmitry Baranchuk 2022-06-27 17:26:08 +0300
f9b6b67b09 [typo] fix typo where run_server with blocks with index 0 would cause server.create to NOT start (start=0) fix-auth-token justheuristic 2022-06-27 15:55:47 +0300
d5c410bb1f fix auth token justheuristic 2022-06-27 15:51:58 +0300
ca3c08acc1

Update README.md justheuristic 2022-06-24 10:05:39 +0300
34b8b86673 disclaimer: this part is a work-in-progress justheuristic 2022-06-23 16:38:54 +0300
1cdf8a77fb basic chained inference (multiple blocks per one RPC call) justheuristic 2022-06-23 16:33:16 +0300
ce9556dcb0 deprecation warning justheuristic 2022-06-23 16:26:54 +0300
d03b38b9eb black-isort justheuristic 2022-06-23 14:40:57 +0300
01b9bced78 black-isort justheuristic 2022-06-22 22:13:21 +0300
0e7afea026 Merge remote-tracking branch 'origin/main' into main justheuristic 2022-06-22 22:02:27 +0300
2eb47cbedd support hosting multiple instances of the same block multiple-experts justheuristic 2022-06-22 22:00:55 +0300
14b6d04b0f install hivemind from pip justheuristic 2022-06-22 17:32:13 +0300
43fdcac6aa Loading a bloom block working. 8bit_blocks Tim Dettmers 2022-06-20 10:07:42 -0700
f3722d52cf

Update README.md justheuristic 2022-06-20 17:02:29 +0300
aaaf0c2dad better testing readme justheuristic 2022-06-20 16:51:20 +0300
83cd4412a1 black-isort justheuristic 2022-06-20 16:50:22 +0300
2bf83b42e5 add testing guide justheuristic 2022-06-20 16:50:12 +0300
b843328b65 mask justheuristic 2022-06-20 16:31:36 +0300
5d8f7be546 causal mask by default justheuristic 2022-06-20 16:24:29 +0300
1ab5fb1630 fetch a specific bloom block without downloading the entire model justheuristic 2022-06-20 15:33:17 +0300
a6fca51212 fetch a specific bloom block without downloading the entire model justheuristic 2022-06-20 15:11:22 +0300
6047a2ffe0 push config and tokenizer separately justheuristic 2022-06-20 14:28:31 +0300
2d55e6e4fe instructions to test distributed inference justheuristic 2022-06-19 22:25:57 +0300
9be7c81b78 instructions to test distributed inference justheuristic 2022-06-19 22:22:01 +0300
cc9a76625d warn about long runtime justheuristic 2022-06-19 22:14:52 +0300
82214699f2 notes on hosting servers justheuristic 2022-06-19 19:34:18 +0300
b6f3bbfd97 black justheuristic 2022-06-19 19:18:46 +0300
84de19fb1a better status logs justheuristic 2022-06-19 19:17:44 +0300
1555d98f66 push converted model to hub justheuristic 2022-06-19 19:13:48 +0300
736f1d1085 push converted model to hub justheuristic 2022-06-19 19:06:35 +0300
15d0ea7129 fix black justheuristic 2022-06-19 17:24:11 +0300
e8241d2915 black everything justheuristic 2022-06-19 17:23:08 +0300
3b9351de1c isort justheuristic 2022-06-19 17:22:57 +0300
ed468af8d6 leave a todo for attention mask justheuristic 2022-06-19 17:22:29 +0300
33358bc52b rpc_inference works inference_chain justheuristic 2022-06-19 17:20:22 +0300
47c308306a TODOs were moved to https://github.com/learning-at-home/bloom-demo/issues/3#issuecomment-1159686069 justheuristic 2022-06-19 16:56:21 +0300
a00ec56ade basic multi-step inference session justheuristic 2022-06-19 16:55:51 +0300
c4d508c00e remove some unnecessary debugprints justheuristic 2022-06-19 14:14:11 +0300
a44cb84f06 basic cache checks (via debugprint) justheuristic 2022-06-19 14:13:45 +0300
fee63bd440 rpc_inference works! justheuristic 2022-06-19 13:51:55 +0300
8092bd31ff swap to int64 (rationale: pytorch does not support uint64) justheuristic 2022-06-19 13:37:13 +0300
62d7fde8af pre-check type justheuristic 2022-06-19 12:58:31 +0300
7fba411dff extended run_serverexample justheuristic 2022-06-17 11:40:49 +0300
20497f81d1 switch to hivemind-master justheuristic 2022-06-17 11:34:50 +0300
5a15c13ca7 switch to hivemind-master justheuristic 2022-06-17 10:36:34 +0300
57f4e0a899 add identity path Pavel Samygin 2022-06-17 10:15:15 +0300
35310698f0 newer hivemind version justheuristic 2022-06-17 10:12:09 +0300
8959727dea add minimalistic benchmarks justheuristic 2022-06-14 15:18:38 +0300
a798ea04a6 add minimalistic benchmarks justheuristic 2022-06-14 15:18:11 +0300
e3a7d5af30 inference mode justheuristic 2022-06-14 14:51:06 +0300
3b16d6ffdb black-isort justheuristic 2022-06-14 13:33:25 +0300
a28ea0aa6f

Merge pull request #9 from learning-at-home/rpc justheuristic 2022-06-14 09:46:42 +0300
14e316b52a black-isort justheuristic 2022-06-14 09:46:14 +0300
eea9287182 RemoteTransformerBlock justheuristic 2022-06-14 09:45:22 +0300
3e9fd63a02 RemoteTransformerBlock justheuristic 2022-06-14 09:45:06 +0300
1cca611c9f undo rename justheuristic 2022-06-14 09:23:32 +0300
7ce7cd7a97 basic backend justheuristic 2022-06-14 08:49:42 +0300
1c49bcb741 basic backend justheuristic 2022-06-14 08:26:05 +0300
3215945882 use logger justheuristic 2022-06-14 08:25:06 +0300
ce5dedd2c7 rename justheuristic 2022-06-14 05:09:13 +0300
8f5d022d18 save hidden size justheuristic 2022-06-14 05:09:07 +0300
e2e9d0e94c memory cache for attention KVs justheuristic 2022-06-13 00:47:55 +0300
e5e8c9ed12 expel all bloom-specific files to src.bloom justheuristic 2022-06-12 21:44:36 +0300
324ea2dc96 save non-transformer params separately justheuristic 2022-06-12 09:35:58 +0300
54cf292374 backend schema justheuristic 2022-06-12 08:40:33 +0300
3ccd0b5e2d account for layer_past in alibi justheuristic 2022-06-12 07:21:17 +0300
fb3bfbb78f optimization TODOs for later justheuristic 2022-06-12 06:54:12 +0300
902bf6400a [temp workaround] create alibi main_fix justheuristic 2022-06-12 06:50:19 +0300
05faa0b3c8 add quantization script for cpu justheuristic 2022-06-12 05:59:11 +0300
ffb56a65ed keep hidden_size as property justheuristic 2022-06-12 05:11:28 +0300
ffce7718ac layer.py -> block.py justheuristic 2022-06-12 05:09:28 +0300
9c929b6f3b layer.py -> bloom_block.py justheuristic 2022-06-12 05:08:18 +0300
79925fc5f7 [more disclaimers] justheuristic 2022-06-12 05:03:16 +0300
fde9d50850 remove slow_but_exact, add quantization justheuristic 2022-06-12 05:00:01 +0300
43399d7898 remove slow_but_exact, add quantization justheuristic 2022-06-12 04:56:26 +0300
51e96ac19b adopt transformers bloom model justheuristic 2022-06-12 04:24:12 +0300
99059ae667 install script justheuristic 2022-06-12 04:23:38 +0300
71717c5f00 Merge remote-tracking branch 'origin/main' into main justheuristic 2022-06-12 03:19:02 +0300
b370b43110 freeze hivemind and transformers versions justheuristic 2022-06-12 03:18:53 +0300
c1a908dc66

Update README.md justheuristic 2022-06-12 03:13:40 +0300
af04479cf9

Initial commit justheuristic 2022-06-12 03:10:27 +0300