René's URL Explorer Experiment


Title: GitHub - microsoft/torchscale: Foundation Architecture for (M)LLMs

Open Graph Title: GitHub - microsoft/torchscale: Foundation Architecture for (M)LLMs

X Title: GitHub - microsoft/torchscale: Foundation Architecture for (M)LLMs

Description: Foundation Architecture for (M)LLMs. Contribute to microsoft/torchscale development by creating an account on GitHub.

Open Graph Description: Foundation Architecture for (M)LLMs. Contribute to microsoft/torchscale development by creating an account on GitHub.

X Description: Foundation Architecture for (M)LLMs. Contribute to microsoft/torchscale development by creating an account on GitHub.

Mail addresses
fuwei@microsoft.com
shumma@microsoft.com

Opengraph URL: https://github.com/microsoft/torchscale

X: @github

direct link

Domain: patch-diff.githubusercontent.com

route-pattern/:user_id/:repository
route-controllerfiles
route-actiondisambiguate
fetch-noncev2:901136e4-1eb1-f150-44c2-5e931e0cdde7
current-catalog-service-hashf3abb0cc802f3d7b95fc8762b94bdcb13bf39634c40c357301c4aa1d67a256fb
request-id8956:39C0A8:806321:A600AA:698D28CA
html-safe-nonceda7bdaddaa26360b9a94d51873739aa3dc01920aee1a8b55414f7799d4b781e7
visitor-payloadeyJyZWZlcnJlciI6IiIsInJlcXVlc3RfaWQiOiI4OTU2OjM5QzBBODo4MDYzMjE6QTYwMEFBOjY5OEQyOENBIiwidmlzaXRvcl9pZCI6IjYwMjg4MzA3NjAzNDkwMTgzMTQiLCJyZWdpb25fZWRnZSI6ImlhZCIsInJlZ2lvbl9yZW5kZXIiOiJpYWQifQ==
visitor-hmac7269fcf83bc13bca4014c67707b540647132492d4dec85fd176c78b049ff1238
hovercard-subject-tagrepository:567185522
github-keyboard-shortcutsrepository,copilot
google-site-verificationApib7-x98H0j5cPqHWwSMm6dNU4GmODRoqxLiDzdx9I
octolytics-urlhttps://collector.github.com/github/collect
analytics-location//
fb:app_id1401488693436528
apple-itunes-appapp-id=1477376905, app-argument=https://github.com/microsoft/torchscale
twitter:imagehttps://opengraph.githubassets.com/95b99a27d57955b6cd9a90a143aa48216fa29bd2cbaaa67e4f1623dcf3549df6/microsoft/torchscale
twitter:cardsummary_large_image
og:imagehttps://opengraph.githubassets.com/95b99a27d57955b6cd9a90a143aa48216fa29bd2cbaaa67e4f1623dcf3549df6/microsoft/torchscale
og:image:altFoundation Architecture for (M)LLMs. Contribute to microsoft/torchscale development by creating an account on GitHub.
og:image:width1200
og:image:height600
og:site_nameGitHub
og:typeobject
hostnamegithub.com
expected-hostnamegithub.com
Nonec25395580e1e3bf82d705e0982a1b24255366088720fef945f1493d5e3e67954
turbo-cache-controlno-preview
go-importgithub.com/microsoft/torchscale git https://github.com/microsoft/torchscale.git
octolytics-dimension-user_id6154722
octolytics-dimension-user_loginmicrosoft
octolytics-dimension-repository_id567185522
octolytics-dimension-repository_nwomicrosoft/torchscale
octolytics-dimension-repository_publictrue
octolytics-dimension-repository_is_forkfalse
octolytics-dimension-repository_network_root_id567185522
octolytics-dimension-repository_network_root_nwomicrosoft/torchscale
turbo-body-classeslogged-out env-production page-responsive
disable-turbofalse
browser-stats-urlhttps://api.github.com/_private/browser/stats
browser-errors-urlhttps://api.github.com/_private/browser/errors
release1fa2bc33fc715bfb2cb9dd8a9cad4f811c16c371
ui-targetfull
theme-color#1e2327
color-schemelight dark

Links:

Skip to contenthttps://patch-diff.githubusercontent.com/microsoft/torchscale#start-of-content
https://patch-diff.githubusercontent.com/
Sign in https://patch-diff.githubusercontent.com/login?return_to=https%3A%2F%2Fgithub.com%2Fmicrosoft%2Ftorchscale
GitHub CopilotWrite better code with AIhttps://github.com/features/copilot
GitHub SparkBuild and deploy intelligent appshttps://github.com/features/spark
GitHub ModelsManage and compare promptshttps://github.com/features/models
MCP RegistryNewIntegrate external toolshttps://github.com/mcp
ActionsAutomate any workflowhttps://github.com/features/actions
CodespacesInstant dev environmentshttps://github.com/features/codespaces
IssuesPlan and track workhttps://github.com/features/issues
Code ReviewManage code changeshttps://github.com/features/code-review
GitHub Advanced SecurityFind and fix vulnerabilitieshttps://github.com/security/advanced-security
Code securitySecure your code as you buildhttps://github.com/security/advanced-security/code-security
Secret protectionStop leaks before they starthttps://github.com/security/advanced-security/secret-protection
Why GitHubhttps://github.com/why-github
Documentationhttps://docs.github.com
Bloghttps://github.blog
Changeloghttps://github.blog/changelog
Marketplacehttps://github.com/marketplace
View all featureshttps://github.com/features
Enterpriseshttps://github.com/enterprise
Small and medium teamshttps://github.com/team
Startupshttps://github.com/enterprise/startups
Nonprofitshttps://github.com/solutions/industry/nonprofits
App Modernizationhttps://github.com/solutions/use-case/app-modernization
DevSecOpshttps://github.com/solutions/use-case/devsecops
DevOpshttps://github.com/solutions/use-case/devops
CI/CDhttps://github.com/solutions/use-case/ci-cd
View all use caseshttps://github.com/solutions/use-case
Healthcarehttps://github.com/solutions/industry/healthcare
Financial serviceshttps://github.com/solutions/industry/financial-services
Manufacturinghttps://github.com/solutions/industry/manufacturing
Governmenthttps://github.com/solutions/industry/government
View all industrieshttps://github.com/solutions/industry
View all solutionshttps://github.com/solutions
AIhttps://github.com/resources/articles?topic=ai
Software Developmenthttps://github.com/resources/articles?topic=software-development
DevOpshttps://github.com/resources/articles?topic=devops
Securityhttps://github.com/resources/articles?topic=security
View all topicshttps://github.com/resources/articles
Customer storieshttps://github.com/customer-stories
Events & webinarshttps://github.com/resources/events
Ebooks & reportshttps://github.com/resources/whitepapers
Business insightshttps://github.com/solutions/executive-insights
GitHub Skillshttps://skills.github.com
Documentationhttps://docs.github.com
Customer supporthttps://support.github.com
Community forumhttps://github.com/orgs/community/discussions
Trust centerhttps://github.com/trust-center
Partnershttps://github.com/partners
GitHub SponsorsFund open source developershttps://github.com/sponsors
Security Labhttps://securitylab.github.com
Maintainer Communityhttps://maintainers.github.com
Acceleratorhttps://github.com/accelerator
Archive Programhttps://archiveprogram.github.com
Topicshttps://github.com/topics
Trendinghttps://github.com/trending
Collectionshttps://github.com/collections
Enterprise platformAI-powered developer platformhttps://github.com/enterprise
GitHub Advanced SecurityEnterprise-grade security featureshttps://github.com/security/advanced-security
Copilot for BusinessEnterprise-grade AI featureshttps://github.com/features/copilot/copilot-business
Premium SupportEnterprise-grade 24/7 supporthttps://github.com/premium-support
Pricinghttps://github.com/pricing
Search syntax tipshttps://docs.github.com/search-github/github-code-search/understanding-github-code-search-syntax
documentationhttps://docs.github.com/search-github/github-code-search/understanding-github-code-search-syntax
Sign in https://patch-diff.githubusercontent.com/login?return_to=https%3A%2F%2Fgithub.com%2Fmicrosoft%2Ftorchscale
Sign up https://patch-diff.githubusercontent.com/signup?ref_cta=Sign+up&ref_loc=header+logged+out&ref_page=%2F%3Cuser-name%3E%2F%3Crepo-name%3E&source=header-repo&source_repo=microsoft%2Ftorchscale
Reloadhttps://patch-diff.githubusercontent.com/microsoft/torchscale
Reloadhttps://patch-diff.githubusercontent.com/microsoft/torchscale
Reloadhttps://patch-diff.githubusercontent.com/microsoft/torchscale
microsoft https://patch-diff.githubusercontent.com/microsoft
torchscalehttps://patch-diff.githubusercontent.com/microsoft/torchscale
Notifications https://patch-diff.githubusercontent.com/login?return_to=%2Fmicrosoft%2Ftorchscale
Fork 223 https://patch-diff.githubusercontent.com/login?return_to=%2Fmicrosoft%2Ftorchscale
Star 3.1k https://patch-diff.githubusercontent.com/login?return_to=%2Fmicrosoft%2Ftorchscale
aka.ms/GeneralAIhttps://aka.ms/GeneralAI
MIT license https://patch-diff.githubusercontent.com/microsoft/torchscale/blob/main/LICENSE
3.1k stars https://patch-diff.githubusercontent.com/microsoft/torchscale/stargazers
223 forks https://patch-diff.githubusercontent.com/microsoft/torchscale/forks
Branches https://patch-diff.githubusercontent.com/microsoft/torchscale/branches
Tags https://patch-diff.githubusercontent.com/microsoft/torchscale/tags
Activity https://patch-diff.githubusercontent.com/microsoft/torchscale/activity
Star https://patch-diff.githubusercontent.com/login?return_to=%2Fmicrosoft%2Ftorchscale
Notifications https://patch-diff.githubusercontent.com/login?return_to=%2Fmicrosoft%2Ftorchscale
Code https://patch-diff.githubusercontent.com/microsoft/torchscale
Issues 29 https://patch-diff.githubusercontent.com/microsoft/torchscale/issues
Pull requests 9 https://patch-diff.githubusercontent.com/microsoft/torchscale/pulls
Actions https://patch-diff.githubusercontent.com/microsoft/torchscale/actions
Projects 0 https://patch-diff.githubusercontent.com/microsoft/torchscale/projects
Models https://patch-diff.githubusercontent.com/microsoft/torchscale/models
Wiki https://patch-diff.githubusercontent.com/microsoft/torchscale/wiki
Security 0 https://patch-diff.githubusercontent.com/microsoft/torchscale/security
Insights https://patch-diff.githubusercontent.com/microsoft/torchscale/pulse
Code https://patch-diff.githubusercontent.com/microsoft/torchscale
Issues https://patch-diff.githubusercontent.com/microsoft/torchscale/issues
Pull requests https://patch-diff.githubusercontent.com/microsoft/torchscale/pulls
Actions https://patch-diff.githubusercontent.com/microsoft/torchscale/actions
Projects https://patch-diff.githubusercontent.com/microsoft/torchscale/projects
Models https://patch-diff.githubusercontent.com/microsoft/torchscale/models
Wiki https://patch-diff.githubusercontent.com/microsoft/torchscale/wiki
Security https://patch-diff.githubusercontent.com/microsoft/torchscale/security
Insights https://patch-diff.githubusercontent.com/microsoft/torchscale/pulse
Brancheshttps://patch-diff.githubusercontent.com/microsoft/torchscale/branches
Tagshttps://patch-diff.githubusercontent.com/microsoft/torchscale/tags
https://patch-diff.githubusercontent.com/microsoft/torchscale/branches
https://patch-diff.githubusercontent.com/microsoft/torchscale/tags
123 Commitshttps://patch-diff.githubusercontent.com/microsoft/torchscale/commits/main/
https://patch-diff.githubusercontent.com/microsoft/torchscale/commits/main/
.github/workflowshttps://patch-diff.githubusercontent.com/microsoft/torchscale/tree/main/.github/workflows
.github/workflowshttps://patch-diff.githubusercontent.com/microsoft/torchscale/tree/main/.github/workflows
exampleshttps://patch-diff.githubusercontent.com/microsoft/torchscale/tree/main/examples
exampleshttps://patch-diff.githubusercontent.com/microsoft/torchscale/tree/main/examples
testshttps://patch-diff.githubusercontent.com/microsoft/torchscale/tree/main/tests
testshttps://patch-diff.githubusercontent.com/microsoft/torchscale/tree/main/tests
torchscalehttps://patch-diff.githubusercontent.com/microsoft/torchscale/tree/main/torchscale
torchscalehttps://patch-diff.githubusercontent.com/microsoft/torchscale/tree/main/torchscale
.gitignorehttps://patch-diff.githubusercontent.com/microsoft/torchscale/blob/main/.gitignore
.gitignorehttps://patch-diff.githubusercontent.com/microsoft/torchscale/blob/main/.gitignore
CODE_OF_CONDUCT.mdhttps://patch-diff.githubusercontent.com/microsoft/torchscale/blob/main/CODE_OF_CONDUCT.md
CODE_OF_CONDUCT.mdhttps://patch-diff.githubusercontent.com/microsoft/torchscale/blob/main/CODE_OF_CONDUCT.md
LICENSEhttps://patch-diff.githubusercontent.com/microsoft/torchscale/blob/main/LICENSE
LICENSEhttps://patch-diff.githubusercontent.com/microsoft/torchscale/blob/main/LICENSE
README.mdhttps://patch-diff.githubusercontent.com/microsoft/torchscale/blob/main/README.md
README.mdhttps://patch-diff.githubusercontent.com/microsoft/torchscale/blob/main/README.md
SECURITY.mdhttps://patch-diff.githubusercontent.com/microsoft/torchscale/blob/main/SECURITY.md
SECURITY.mdhttps://patch-diff.githubusercontent.com/microsoft/torchscale/blob/main/SECURITY.md
SUPPORT.mdhttps://patch-diff.githubusercontent.com/microsoft/torchscale/blob/main/SUPPORT.md
SUPPORT.mdhttps://patch-diff.githubusercontent.com/microsoft/torchscale/blob/main/SUPPORT.md
setup.pyhttps://patch-diff.githubusercontent.com/microsoft/torchscale/blob/main/setup.py
setup.pyhttps://patch-diff.githubusercontent.com/microsoft/torchscale/blob/main/setup.py
READMEhttps://patch-diff.githubusercontent.com/microsoft/torchscale
Code of conducthttps://patch-diff.githubusercontent.com/microsoft/torchscale
MIT licensehttps://patch-diff.githubusercontent.com/microsoft/torchscale
Securityhttps://patch-diff.githubusercontent.com/microsoft/torchscale
https://patch-diff.githubusercontent.com/microsoft/torchscale#torchscale---a-library-of-foundation-architectures
https://github.com/microsoft/torchscale/blob/main/LICENSE
https://pypi.org/project/torchscale
DeepNethttps://arxiv.org/abs/2203.00555
Foundation Transformers (Magneto)https://arxiv.org/abs/2210.06423
Length-Extrapolatablehttps://arxiv.org/abs/2212.10554
X-MoEhttps://arxiv.org/abs/2204.09179
https://patch-diff.githubusercontent.com/microsoft/torchscale#the-revolution-of-model-architecture
BitNethttps://arxiv.org/abs/2310.11453
RetNethttps://arxiv.org/abs/2307.08621
LongNethttps://arxiv.org/abs/2307.02486
https://patch-diff.githubusercontent.com/microsoft/torchscale#news
LongNethttps://patch-diff.githubusercontent.com/microsoft/torchscale/blob/main/torchscale/model/LongNet.py
LongViThttps://patch-diff.githubusercontent.com/microsoft/torchscale/blob/main/examples/longvit/README.md
Paperhttps://arxiv.org/abs/2211.13184
PyPIhttps://pypi.org/project/torchscale/
https://patch-diff.githubusercontent.com/microsoft/torchscale#installation
Flash Attentionhttps://github.com/Dao-AILab/flash-attention
xFormershttps://github.com/facebookresearch/xformers
https://patch-diff.githubusercontent.com/microsoft/torchscale#getting-started
Flash Attentionhttps://github.com/Dao-AILab/flash-attention
https://patch-diff.githubusercontent.com/microsoft/torchscale#key-features
DeepNorm to improve the training stability of Post-LayerNorm Transformershttps://arxiv.org/abs/2203.00555
SubLN for the model generality and the training stabilityhttps://arxiv.org/abs/2210.06423
X-MoE: efficient and finetunable sparse MoE modelinghttps://arxiv.org/abs/2204.09179
Multiway architecture for multimodalityhttps://arxiv.org/abs/2208.10442
Extrapolatable position embedding (Xpos)https://arxiv.org/abs/2212.10554
Relative position biashttps://arxiv.org/abs/1910.10683
SparseClip: improving the gradient clipping for sparse MoE modelshttps://arxiv.org/abs/2211.13184
sample codehttps://patch-diff.githubusercontent.com/microsoft/torchscale/blob/main/examples/fairseq/utils/sparse_clip.py
Retentive Network: A Successor to Transformer for Large Language Modelshttps://arxiv.org/abs/2307.08621
LongNet: Scaling Transformers to 1,000,000,000 Tokenshttps://arxiv.org/abs/2307.02486
https://patch-diff.githubusercontent.com/microsoft/torchscale#examples
Decoder/GPThttps://patch-diff.githubusercontent.com/microsoft/torchscale/blob/main/examples/fairseq/README.md#example-gpt-pretraining
Encoder-Decoder/Neural Machine Translationhttps://patch-diff.githubusercontent.com/microsoft/torchscale/blob/main/examples/fairseq/README.md#example-machine-translation
Encoder/BERThttps://patch-diff.githubusercontent.com/microsoft/torchscale/blob/main/examples/fairseq/README.md#example-bert-pretraining
LongViThttps://patch-diff.githubusercontent.com/microsoft/torchscale/blob/main/examples/longvit/README.md
Multiway Transformers/BEiT-3https://github.com/microsoft/unilm/tree/master/beit3
DeepSpeedhttps://github.com/microsoft/DeepSpeed
Megatron-LMhttps://github.com/NVIDIA/Megatron-LM
https://patch-diff.githubusercontent.com/microsoft/torchscale#acknowledgments
FairSeqhttps://github.com/facebookresearch/fairseq
UniLMhttps://github.com/microsoft/unilm
https://patch-diff.githubusercontent.com/microsoft/torchscale#citations
https://patch-diff.githubusercontent.com/microsoft/torchscale#contributing
https://cla.opensource.microsoft.comhttps://cla.opensource.microsoft.com
Microsoft Open Source Code of Conducthttps://opensource.microsoft.com/codeofconduct/
Code of Conduct FAQhttps://opensource.microsoft.com/codeofconduct/faq/
https://patch-diff.githubusercontent.com/microsoft/torchscale#trademarks
Microsoft's Trademark & Brand Guidelineshttps://www.microsoft.com/en-us/legal/intellectualproperty/trademarks/usage/general
aka.ms/GeneralAIhttps://aka.ms/GeneralAI
machine-learning https://patch-diff.githubusercontent.com/topics/machine-learning
natural-language-processing https://patch-diff.githubusercontent.com/topics/natural-language-processing
translation https://patch-diff.githubusercontent.com/topics/translation
computer-vision https://patch-diff.githubusercontent.com/topics/computer-vision
transformer https://patch-diff.githubusercontent.com/topics/transformer
speech-processing https://patch-diff.githubusercontent.com/topics/speech-processing
multimodal https://patch-diff.githubusercontent.com/topics/multimodal
pretrained-language-model https://patch-diff.githubusercontent.com/topics/pretrained-language-model
Readme https://patch-diff.githubusercontent.com/microsoft/torchscale#readme-ov-file
MIT license https://patch-diff.githubusercontent.com/microsoft/torchscale#MIT-1-ov-file
Code of conduct https://patch-diff.githubusercontent.com/microsoft/torchscale#coc-ov-file
Security policy https://patch-diff.githubusercontent.com/microsoft/torchscale#security-ov-file
Please reload this pagehttps://patch-diff.githubusercontent.com/microsoft/torchscale
Activityhttps://patch-diff.githubusercontent.com/microsoft/torchscale/activity
Custom propertieshttps://patch-diff.githubusercontent.com/microsoft/torchscale/custom-properties
3.1k starshttps://patch-diff.githubusercontent.com/microsoft/torchscale/stargazers
41 watchinghttps://patch-diff.githubusercontent.com/microsoft/torchscale/watchers
223 forkshttps://patch-diff.githubusercontent.com/microsoft/torchscale/forks
Report repository https://patch-diff.githubusercontent.com/contact/report-content?content_url=https%3A%2F%2Fgithub.com%2Fmicrosoft%2Ftorchscale&report=microsoft+%28user%29
Releaseshttps://patch-diff.githubusercontent.com/microsoft/torchscale/releases
Packages 0https://patch-diff.githubusercontent.com/orgs/microsoft/packages?repo_name=torchscale
Please reload this pagehttps://patch-diff.githubusercontent.com/microsoft/torchscale
Contributors 15https://patch-diff.githubusercontent.com/microsoft/torchscale/graphs/contributors
Please reload this pagehttps://patch-diff.githubusercontent.com/microsoft/torchscale
Python 100.0% https://patch-diff.githubusercontent.com/microsoft/torchscale/search?l=python
https://github.com
Termshttps://docs.github.com/site-policy/github-terms/github-terms-of-service
Privacyhttps://docs.github.com/site-policy/privacy-policies/github-privacy-statement
Securityhttps://github.com/security
Statushttps://www.githubstatus.com/
Communityhttps://github.community/
Docshttps://docs.github.com/
Contacthttps://support.github.com?tags=dotcom-footer

Viewport: width=device-width

URLs of crawlers that visited me.