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

bb8519bad5 capitalization justheuristic 2022-07-15 17:13:30 +0300
c2f446a1f1 setup black/isort justheuristic 2022-07-15 17:12:23 +0300
a3def86444 minimalistic tests justheuristic 2022-07-15 17:06:31 +0300
a41f3b8c39 black + isort client-attempt2 justheuristic 2022-07-15 16:26:28 +0300
ca21935c77 black + isort justheuristic 2022-07-15 16:26:04 +0300
14cbc17150 fix type check justheuristic 2022-07-15 16:24:38 +0300
7e9f337a63

Remove excess line from readme Alexander Borzunov 2022-07-14 22:27:17 +0400
db966a76dd

rm heuristic for num_handlers Dmitry Baranchuk 2022-07-14 02:35:23 +0300
f114a6d417

set default num_handlers=16 Dmitry Baranchuk 2022-07-14 02:32:58 +0300
f3cf5f4d8d Fix choose_best_blocks() Aleksandr Borzunov 2022-07-13 22:59:01 +0000
afce0621b5 preliminary shallow prompt tuning dbaranchuk 2022-07-13 20:59:10 +0300
75856e4769

Measure and cache network & compute throughput (#21) Alexander Borzunov 2022-07-13 05:46:26 +0400
7b877d64ab Add a hack to avoid race conditions measure-throughput Aleksandr Borzunov 2022-07-13 01:40:04 +0000
619da54a7c Tolerate exceptions during reading cache Aleksandr Borzunov 2022-07-13 01:08:42 +0000
b65409398a Change project_name to bloomd Aleksandr Borzunov 2022-07-13 01:04:48 +0000
c10e505324 Measure and cache throughput by default Aleksandr Borzunov 2022-07-12 23:29:29 +0000
94f5e366b9 Draft measuring throughput Aleksandr Borzunov 2022-07-12 22:19:27 +0000
ac7df18dfa

Merge pull request #19 from learning-at-home/lm_head Dmitry Baranchuk 2022-07-12 14:25:24 +0300
fd0bf064f3

minor refactoring lm_head Dmitry Baranchuk 2022-07-12 14:22:11 +0300
aba43f1308

Implement block selection on servers (#20) Alexander Borzunov 2022-07-12 14:42:30 +0400
abcfb17a10 Rename src.server.{load_balancing => block_selection} load-balancing Aleksandr Borzunov 2022-07-12 10:33:48 +0000
0336a04082 Fix format bugs on client side Aleksandr Borzunov 2022-07-12 02:05:34 +0000
d6889cbe96 Fix load balancing race condition when starting multiple servers at once Aleksandr Borzunov 2022-07-12 00:40:33 +0000
f73c655c82 Make throughput obligatory Aleksandr Borzunov 2022-07-11 23:49:29 +0000
7d489784e6 Fix runtime errors Aleksandr Borzunov 2022-07-11 15:33:35 +0000
be71cf7992 Start implementing load balancing Aleksandr Borzunov 2022-07-11 16:42:44 +0400
21e1f42f04 mv set_requires_grad to remote_model dbaranchuk 2022-07-10 23:41:05 +0300
5168a3405a fix comments dbaranchuk 2022-07-10 20:35:13 +0300
79280c4371 refactoring dbaranchuk 2022-07-10 20:27:38 +0300
6bffeff0a1 fix dbaranchuk 2022-07-10 20:17:11 +0300
b3cc9e0d99 add LM head for DistributedBloomCausalLM dbaranchuk 2022-07-10 15:13:46 +0300
df42822f26 LM head for CausalLM & chunked forward dbaranchuk 2022-07-10 15:10:13 +0300
3b6d94ffef design doc sequence justheuristic 2022-07-08 23:44:12 +0300
0613095168 design-doc justheuristic 2022-07-08 23:38:15 +0300
f055135b08

rm prefix Dmitry Baranchuk 2022-07-08 21:59:25 +0300
d651d0c28b undo fix demo-1 justheuristic 2022-07-08 19:45:26 +0300
deecdff2ac compare justheuristic 2022-07-08 19:44:10 +0300
efa0d16714 rm prefix from tests justheuristic 2022-07-08 19:39:56 +0300
4eadd00a2c rm prefix from tests justheuristic 2022-07-08 19:11:55 +0300
1c68670d06 it works standardize justheuristic 2022-07-08 19:05:57 +0300
a8357faa45 WIP diff justheuristic 2022-07-07 22:08:00 +0300
477da687f9 WIP justheuristic 2022-07-07 21:05:09 +0300
2e90ac30a0 use default prefix in readme justheuristic 2022-07-07 13:22:03 +0300
5695897620 fix imports justheuristic 2022-07-07 04:13:20 +0300
88c1bf9896 black-isort justheuristic 2022-07-07 03:49:53 +0300
3223e8b19b straighten import order justheuristic 2022-07-07 03:49:19 +0300
de556c99be straighten import order justheuristic 2022-07-07 03:49:04 +0300
c792f50b9c fix import order justheuristic 2022-07-07 03:42:28 +0300
90d65e58aa set default DHT prefix justheuristic 2022-07-07 03:34:58 +0300
41e5a95e8e set client branch to main by default; remove the concept of base branch (redundant) justheuristic 2022-07-07 03:18:10 +0300
899cefe588 set client branch to main by default; remove the concept of base branch (redundant) justheuristic 2022-07-07 03:16:47 +0300
4695071ad2 WIP: make DistributedBloom compliant with HF interface justheuristic 2022-07-07 03:11:28 +0300
6c437c9249 use main as client branch justheuristic 2022-07-07 03:08:41 +0300
e32208c954 black-isort justheuristic 2022-07-07 01:06:03 +0300
4ad845bce3 black-isort justheuristic 2022-07-07 01:04:47 +0300
0f9cd687d4

Merge pull request #18 from learning-at-home/rpc justheuristic 2022-07-07 00:58:10 +0300
4cb986f680 add chained rpc_forward & rpc_backward rpc Dmitry Baranchuk 2022-07-06 19:44:28 +0300
0b5a68983f

Merge pull request #17 from learning-at-home/update-model Dmitry Baranchuk 2022-07-05 16:41:36 +0300
29999a6691 rm debug print update-model Dmitry Baranchuk 2022-07-05 02:02:19 +0300
e66ab6f1f2 design interface & refactoring Dmitry Baranchuk 2022-07-05 01:54:47 +0300
be83e6d0cb refactoring Dmitry Baranchuk 2022-07-04 22:43:51 +0300
6a603f9cd6 set requires_grad=False, lm_layer -> h @ word_embeddings, rm lm_layer from comverted_model Dmitry Baranchuk 2022-07-04 21:26:06 +0300
d969172208 set requires_grad=False, lm_layer -> h @ word_embeddings, rm lm_layer from comverted_model Dmitry Baranchuk 2022-07-04 21:18:29 +0300
30d8bf3301 Merge branch 'main' of github.com:learning-at-home/bloom-demo into main justheuristic 2022-07-01 16:58:28 +0300
792dc4bcf8 review Aleksandr Borzunov 2022-07-01 11:55:48 +0300
8de7c1687b

list latest additions justheuristic 2022-07-01 03:57:21 +0300
d42e8abd38 Merge branch 'client' into main justheuristic 2022-07-01 03:53:54 +0300
d688cb0d22 stupid, slow, fragile, but correct full model inference client justheuristic 2022-07-01 03:53:08 +0300
a6c4a606e0 compare logits to logits justheuristic 2022-07-01 03:48:36 +0300
d0c7f2a886 test full model exact match justheuristic 2022-07-01 03:38:38 +0300
3f42b3fb8d run inference with no grad justheuristic 2022-07-01 02:49:02 +0300
db3ad89c2e temporary fix for info justheuristic 2022-07-01 02:42:56 +0300
6113a7e955 create alibi inside each block justheuristic 2022-07-01 02:36:14 +0300
8ff45d136d check for absent args justheuristic 2022-07-01 02:34:10 +0300
f8b7aaece4 proper __len__ justheuristic 2022-07-01 02:32:29 +0300
dfc7449cd5 fix hanging justheuristic 2022-07-01 02:23:33 +0300
9c31c16ecd review artek0chumak 2022-06-29 20:31:25 +0300
75fdd9d2cd typo justheuristic 2022-06-29 15:32:48 +0300
4c92d8636f forward exc details justheuristic 2022-06-29 15:31:11 +0300
e7f716502c inference session justheuristic 2022-06-29 15:30:36 +0300
a7be94e6e7 debug-check justheuristic 2022-06-29 15:27:17 +0300
217f109723 fix reference justheuristic 2022-06-29 15:06:10 +0300
a4bdce32c1 fix reference justheuristic 2022-06-29 14:41:54 +0300
ec477b910b rename justheuristic 2022-06-29 14:40:11 +0300
e38ab3f134 typing fix justheuristic 2022-06-29 14:27:00 +0300
b78d713347 refactor, add swarm info Aleksandr Borzunov 2022-06-29 14:26:47 +0300
d7baa9997d rm deprecated files Dmitry Baranchuk 2022-06-29 13:56:44 +0300
f60a7dd183 deploy swarm on local & remote machines Dmitry Baranchuk 2022-06-29 13:52:43 +0300
331591c915 less intrusive warnings justheuristic 2022-06-29 11:31:23 +0300
9c492bbe8c Infer prefix by defaukt justheuristic 2022-06-29 11:28:13 +0300
19ae71e8fc from_pretrained justheuristic 2022-06-29 11:21:18 +0300
eea6fbb318 check for past key values properly justheuristic 2022-06-29 11:09:49 +0300
3f32912937 check for past key values properly justheuristic 2022-06-29 11:08:00 +0300
7903bd8f9f check for none justheuristic 2022-06-29 11:05:21 +0300
471e47c0f5 black-isort justheuristic 2022-06-29 10:55:13 +0300
7d68f6b9a4 fix model creation justheuristic 2022-06-29 10:53:21 +0300
828291788e fix import cycle justheuristic 2022-06-29 10:47:11 +0300
5849cea28c prototype remote sequential justheuristic 2022-06-29 10:45:08 +0300
775f5b25cb

fix use_auth_token Dmitry Baranchuk 2022-06-28 21:00:34 +0300
6e3db6bed6 black-isort justheuristic 2022-06-28 13:16:03 +0300