Commit Graph

Select branches

Hide Pull Requests

main

#112

#113

#163

#168

#172

#172

#193

#2

#206

#21

#225

#229

#230

#232

#234

#271

#33

#331

#333

#341

#342

#359

#360

#364

#366

#367

#371

#372

#375

#375

#376

#376

#377

#377

#379

#381

#382

#383

#386

#387

#388

#390

#391

#391

#392

#395

#399

#408

#410

#410

#419

#422

#426

#426

#428

#429

#430

#431

#432

#434

#437

#437

#440

#441

#444

#444

#447

#448

#459

#461

#461

#467

#469

#469

#481

#481

#486

#488

#488

#496

#499

#499

#5

#506

#519

#528

#529

#530

#531

#533

#533

#549

#555

#556

#561

#563

#564

#564

#565

#570

#570

#580

#584

#593

#600

#607

#611

#612

#612

#616

#617

#618

#618

#627

#633

#633

#636

#641

#656

#657

#662

#662

#666

#671

#674

#674

#678

#680

#681

#684

#684

#687

#690

#699

#699

#700

#701

#702

#702

#717

#717

#718

#720

#729

#732

#735

#736

#747

#747

#749

#749

#751

#751

#753

#754

#756

#762

#764

#768

#769

#770

#773

#785

#786

#791

#792

#793

#796

#798

#799

#803

#804

#809

#809

#816

#818

#831

#833

#834

#834

#844

#844

#845

#845

#861

#861

#862

#862

#863

#863

#865

#865

#866

#866

#867

#867

#869

#869

#876

#876

#877

#877

#880

#880

#885

#885

#886

#886

#887

#897

#899

#899

#9

#900

#900

Mono Color

• e965eec9c0 [200~feat: Added logging, parallel processing, and CPU processing option for FP8 to BF16 conversion #461 Anand 2025-01-29 22:32:59 +0530
• f57c42a8b8
  update README #448 Thomas 2025-01-29 08:41:36 +0100
• 9d5abb844f Added various error handlers and Issue templates. #447 Ankur Halder 2025-01-29 12:57:39 +0530
• de7df86119 Refactored the codebase by defining seperate classes for different operations and implemented better type safety pratiyankkumar 2025-01-29 10:37:09 +0530
• 760d22821f
  Add syntax highlighting to requirements code block #440 Spenser Black 2025-01-28 18:07:15 -0500
• af8bbe6372 Cleanup README Alimi Faith 2025-01-28 23:05:01 +0000
• 7e137bb39d Add Troubleshooting Section to README Dhieu 2025-01-28 23:49:43 +0300
• 29621f859c
  OCD level super minor fix for consistent capitalization of term Multi-Token Prediction #434 Peter Makadi 2025-01-28 21:06:48 +0100
• 82fdce11de
  Update README.md #431 Nodoubtz 2025-01-28 14:09:22 -0500
• 9f64a6a465
  Create google.yml #430 Nodoubtz 2025-01-28 14:05:40 -0500
• 06f332349f
  Create python-app.yml Nodoubtz 2025-01-28 14:04:03 -0500
• ec9eb26266
  Update README.md #429 Nodoubtz 2025-01-28 13:46:52 -0500
• 507611b83d
  Update generate.py #428 niteoliveira 2025-01-28 15:36:59 -0300
• b874933ce7
  Merge 38333fb817 into b5d872ead0 #426 Utsav-pal 2025-01-28 23:54:54 +0530
• 38333fb817
  Update generate.py: Add parallel processing for token generation #426 Utsav-pal 2025-01-28 23:54:11 +0530
• 943a1fc922
  add link to issues #422 musvaage 2025-01-28 11:14:51 -0600
• bb999d6614
  Update README.md #419 joao57 2025-01-28 13:23:01 -0300
• 6784e1976d Fix TOC links to correctly link to headings in Markdown #364 Dhieu 2025-01-28 17:14:35 +0300
• 8a65a6ae38
  Update requirements.txt #410 p1r4t4 2025-01-28 09:54:24 -0300
• 2756e130c2 clarify assertion error #408 Roman Fitzjalen 2025-01-28 13:16:54 +0100
• 1e4c1219d3
  Update README.md #399 Let Avocado 2025-01-28 12:13:47 +0500
• 41029d972d Added Try-Catch and Memory Optimization in Convert.py #395 AzazAhmedLipu79 2025-01-28 12:15:22 +0600
• c7b49d729c
  Update CITATION.cff #392 w22035 2025-01-27 22:13:00 -0600
• 70ff909fdc Refactored convert.py #391 pratiyankkumar 2025-01-28 09:20:16 +0530
• 43367a81e1 style: Ruff format for pep guidelines #390 Harlan D Heilman 2025-01-27 19:31:11 -0800
• cb7d4d7e62 build: Add python version to requirements.txt Harlan D Heilman 2025-01-27 19:29:09 -0800
• 1eed9a5d32 build: Added tqdm to requirements.txt Harlan D Heilman 2025-01-27 19:25:02 -0800
• e95bcb8064
  Update README_WEIGHTS.md #388 Hyunho Lee 2025-01-28 11:50:16 +0900
• af62bffeff
  Update generate.py #387 Cristian Cezar Moisés 2025-01-27 23:26:23 -0300
• e1ed2e8465
  Update fp8_cast_bf16.py Cristian Cezar Moisés 2025-01-27 23:24:46 -0300
• 6e51b03eb1
  Update convert.py Cristian Cezar Moisés 2025-01-27 23:23:28 -0300
• 6e1d0ed9c6
  Update model.py Cristian Cezar Moisés 2025-01-27 23:21:33 -0300
• 18323417c1
  Update kernel.py Cristian Cezar Moisés 2025-01-27 23:19:26 -0300
• ebbbf84d35
  Update generate.py Cristian Cezar Moisés 2025-01-27 23:16:21 -0300
• f3a55f92c2 Masking: avoid modifying tensor in-place to improve performance #386 Christopher Harrison 2025-01-28 01:35:50 +0000
• eee820cc36
  Update fp8_cast_bf16.py Cristian Cezar Moisés 2025-01-27 23:13:11 -0300
• a26fca4a41
  Update convert.py Cristian Cezar Moisés 2025-01-27 23:10:08 -0300
• b172bbe418 changed format to md #381 Ankush1oo8 2025-01-28 03:09:28 +0530
• 7c93e20c7e
  Update README.md #383 Muhammad Noraeii 2025-01-28 01:02:19 +0330
• f39f3697af
  Create django.yml #754 #382 Nodoubtz 2025-01-27 16:19:40 -0500
• 90cadefb40 Fixed Issue 380 Ankush1oo8 2025-01-28 00:31:26 +0530
• 0b39205aed Fix typos and ensure consistency in documentation #379 Abenezer Anglo 2025-01-27 18:50:55 +0100
• 39165b2151
  Merge da0693199d into b5d872ead0 #377 codecodecodephone 2025-01-27 16:50:57 +0000
• 0f1eee6ae6
  Merge da0693199d into b5d872ead0 #376 codecodecodephone 2025-01-27 16:47:44 +0000
• da0693199d
  Create python-package.yml #377 #376 codecodecodephone 2025-01-27 16:47:30 +0000
• a7151e67fb Add robust MoE implementation with dynamic shapes #375 agentmarketbot 2025-01-27 15:59:02 +0000
• ab320a5ddc
  Create xxx.py #372 Shouvik702 2025-01-27 20:06:13 +0530
• 3da1470312
  Create xxx.py #371 Shouvik703 2025-01-27 19:58:16 +0530
• c47ecaa800
  Update model.py #367 Pedro Dessanti 2025-01-27 10:36:57 -0300
• 9bf00671cf
  Update model.py Pedro Dessanti 2025-01-27 09:04:34 -0300
• 2bf4595d13
  Update model.py #366 Pedro Dessanti 2025-01-27 08:58:59 -0300
• ddc501b80e Add table of contents to README Dhieu 2025-01-27 14:18:17 +0300
• 30b7c65fb6
  Update README.md #360 Afueth Thomas 2025-01-27 15:16:42 +0530
• 81969b0a06
  Update README.md #359 Afueth Thomas 2025-01-27 15:11:49 +0530
• b5d872ead0
  Merge pull request #341 from enochkan/main Huang Panpan 2025-01-26 09:29:50 +0800
• 4186dd3425 some changes #342 saifi 2025-01-25 23:40:57 +0100
• 53d8dc9966 docs: Update system requirements with GitHub Markdown callout #341 enoch kan 2025-01-25 22:29:54 +0000
• 722e6885ef docs: Improve system requirements section formatting enoch kan 2025-01-25 22:26:48 +0000
• 53b055bc1e docs: Add system requirements for DeepSeek-Infer demo enoch kan 2025-01-25 22:21:51 +0000
• a1ca60c540
  Update requirements.txt #333 @Infer 2025-01-24 22:50:58 +0630
• 8a45dade7b
  simplify loop in convert.py #331 qpwo 2025-01-24 01:18:42 -0800
• 8c40067fb2
  make convert.py use multiple processes qpwo 2025-01-24 01:12:19 -0800
• 7117f260e9 mask标记声明 #271 wanglei 2025-01-14 15:29:06 +0800
• ee4c4ea32b
  Merge pull request #234 from wangfuchun-fc/patch-1 Xingkai Yu 2025-01-07 17:53:28 +0800
• 25109d2ccd
  Merge pull request #230 from jacksonpradolima/main Huang Panpan 2025-01-07 14:05:15 +0800
• fdbd5be754
  Merge pull request #193 from enochkan/main Huang Panpan 2025-01-07 14:02:11 +0800
• 3779a89770
  fix: fix readme doc typo. #234 wangfuchun-fc 2025-01-06 22:00:32 +0800
• cd28bb1bf4
  Merge pull request #1 from twlhitesh/improve-accessibility #229 Hitesh Yadav 2025-01-06 15:54:11 +0530
• 7d95c3e5ec Improve accessibility for CAPTCHA challenges in DeepSeek v3 #232 Hitesh Yadav 2025-01-06 15:53:37 +0530
• c070549279 Add CITATION.cff to provide citation metadata #230 Jackson Antonio do Prado Lima 2025-01-05 21:46:37 -0300
• bc77f22afc Updated model.py docstrings #193 enoch kan 2025-01-05 18:24:31 +0000
• a1296f099e Enhance documentation and update .gitignore for model conversion scripts enoch kan 2025-01-05 18:18:18 +0000
• bc9459df40 refactor(inference): modularize model architecture for improved maintainability Hitesh Yadav 2025-01-05 16:28:10 +0530
• fd011c11aa torch rmsnorm GeeeekExplorer 2025-01-05 14:33:48 +0800
• dbd2938f1b
  Create azure-webapps-python.yml #225 shhmfa 2025-01-04 10:07:01 -0500
• 9b288b86cc
  Update README.md Xingkai Yu 2025-01-03 15:30:48 +0800
• 0d16ea24c8
  Merge pull request #206 from kutt/patch-1 Huang Panpan 2025-01-03 09:48:03 +0800
• 21bc231f32
  use alert formatting for notes in readme #206 kutt 2025-01-02 15:02:52 +0100
• f5fb13ee14
  Created fuzz_target.py #168 Shivam7-1 2024-12-31 16:10:31 +0530
• 8710ec2ecb
  require model-parallel in convert.py Xingkai Yu 2024-12-31 18:05:55 +0800
• 8941732439
  Create python-app.yml #172 #163 Jafar Saad 2024-12-31 14:35:29 +0700
• 7c2466b310
  Update issue templates Huang Panpan 2024-12-31 14:49:05 +0800
• dd6882bc3d
  Delete LICENSE-MODEL #113 gogo67xxxggg 2024-12-30 15:20:45 -0600
• ba602e3800
  Delete .github/workflows directory #112 gogo67xxxggg 2024-12-30 15:07:59 -0600
• 641ed202ec
  Create python-package-conda.yml gogo67xxxggg 2024-12-30 15:07:35 -0600
• 1b8e18cc29
  Merge pull request #21 from eltociear/patch-1 Huang Panpan 2024-12-30 15:03:30 +0800
• 94410f8d58
  Merge pull request #33 from zhyncs/main Haswell Iris 2024-12-30 14:37:38 +0800
• 68d0061937 upd #33 zhyncs 2024-12-30 14:25:28 +0800
• 2fc98d1cdf upd zhyncs 2024-12-30 14:21:00 +0800
• a1edf4138e upd zhyncs 2024-12-30 14:18:00 +0800
• 8638950ec2 docs: update SGLang usage zhyncs 2024-12-30 14:13:27 +0800
• 83dd18eda4
  Update README.md DeepSeekDDM 2024-12-30 11:04:14 +0800
• 710c8b8b6e
  docs: update README.md #21 Ikko Eltociear Ashimine 2024-12-29 00:43:11 +0900
• 8f1c9488b5
  handle missing scale_inv_name (#2) Yang Wang 2024-12-27 09:34:38 +0800
• c8087bd8b8
  Merge pull request #9 from simon-mo/vllm Huang Panpan 2024-12-27 09:16:09 +0800
• e2c15caf04 add version #9 simon-mo 2024-12-26 17:11:31 -0800
• cf47874d8e Docs: add vLLM as supported engine simon-mo 2024-12-26 17:10:33 -0800
• 6e7c5ee471 remove interface #5 AK391 2024-12-26 18:09:56 +0100
• 2ab082f2f5 add gradio app AK391 2024-12-26 17:25:34 +0100
• 65d8f5f1e9
  Add CUDA cache clearing in memory management #2 Yang Wang 2024-12-26 23:18:39 +0800