René's URL Explorer Experiment


Title: GitHub - ModelTC/SageAttention: Quantized Attention achieves speedup of 2-5x and 3-11x compared to FlashAttention and xformers, without lossing end-to-end metrics across language, image, and video models.

Open Graph Title: GitHub - ModelTC/SageAttention: Quantized Attention achieves speedup of 2-5x and 3-11x compared to FlashAttention and xformers, without lossing end-to-end metrics across language, image, and video models.

X Title: GitHub - ModelTC/SageAttention: Quantized Attention achieves speedup of 2-5x and 3-11x compared to FlashAttention and xformers, without lossing end-to-end metrics across language, image, and video models.

Description: Quantized Attention achieves speedup of 2-5x and 3-11x compared to FlashAttention and xformers, without lossing end-to-end metrics across language, image, and video models. - ModelTC/SageAttention

Open Graph Description: Quantized Attention achieves speedup of 2-5x and 3-11x compared to FlashAttention and xformers, without lossing end-to-end metrics across language, image, and video models. - ModelTC/SageAttention

X Description: Quantized Attention achieves speedup of 2-5x and 3-11x compared to FlashAttention and xformers, without lossing end-to-end metrics across language, image, and video models. - ModelTC/SageAttention

Opengraph URL: https://github.com/ModelTC/SageAttention

X: @github

direct link

Domain: patch-diff.githubusercontent.com

route-pattern/:user_id/:repository
route-controllerfiles
route-actiondisambiguate
fetch-noncev2:562a79d0-eec9-1aa3-937f-9e9fa3448d66
current-catalog-service-hashf3abb0cc802f3d7b95fc8762b94bdcb13bf39634c40c357301c4aa1d67a256fb
request-idB6AA:3F96B:688C131:8E34F4D:698D06BB
html-safe-noncefecd8c390c2b72c4c29121376154a839d1c1d7623709b8c55d02d96ffa1949ae
visitor-payloadeyJyZWZlcnJlciI6IiIsInJlcXVlc3RfaWQiOiJCNkFBOjNGOTZCOjY4OEMxMzE6OEUzNEY0RDo2OThEMDZCQiIsInZpc2l0b3JfaWQiOiI2ODA1NTQ1NjkzMDI2MDc1NDciLCJyZWdpb25fZWRnZSI6ImlhZCIsInJlZ2lvbl9yZW5kZXIiOiJpYWQifQ==
visitor-hmac74b9f88cd4719e10ca058bd89e564000e04a7fc1bc2fb0b9aff95967b23440ec
hovercard-subject-tagrepository:1038472084
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/ModelTC/SageAttention
twitter:imagehttps://opengraph.githubassets.com/5032db304777a89d0947c3f12a4519571948e4d37d359e09e2e5c0f602e08c8e/ModelTC/SageAttention
twitter:cardsummary_large_image
og:imagehttps://opengraph.githubassets.com/5032db304777a89d0947c3f12a4519571948e4d37d359e09e2e5c0f602e08c8e/ModelTC/SageAttention
og:image:altQuantized Attention achieves speedup of 2-5x and 3-11x compared to FlashAttention and xformers, without lossing end-to-end metrics across language, image, and video models. - ModelTC/SageAttention
og:image:width1200
og:image:height600
og:site_nameGitHub
og:typeobject
hostnamegithub.com
expected-hostnamegithub.com
Nonef2da95634bce8a94cfa4123788169bfabdf845fd1d790fbaaaaab09dcfebdf28
turbo-cache-controlno-preview
go-importgithub.com/ModelTC/SageAttention git https://github.com/ModelTC/SageAttention.git
octolytics-dimension-user_id69665675
octolytics-dimension-user_loginModelTC
octolytics-dimension-repository_id1038472084
octolytics-dimension-repository_nwoModelTC/SageAttention
octolytics-dimension-repository_publictrue
octolytics-dimension-repository_is_forktrue
octolytics-dimension-repository_parent_id867007699
octolytics-dimension-repository_parent_nwothu-ml/SageAttention
octolytics-dimension-repository_network_root_id867007699
octolytics-dimension-repository_network_root_nwothu-ml/SageAttention
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
releasec21843b18feba17d11efb1895a7db61e8672f2cf
ui-targetfull
theme-color#1e2327
color-schemelight dark

Links:

Skip to contenthttps://patch-diff.githubusercontent.com/ModelTC/SageAttention#start-of-content
https://patch-diff.githubusercontent.com/
Sign in https://patch-diff.githubusercontent.com/login?return_to=https%3A%2F%2Fgithub.com%2FModelTC%2FSageAttention
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%2FModelTC%2FSageAttention
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=ModelTC%2FSageAttention
Reloadhttps://patch-diff.githubusercontent.com/ModelTC/SageAttention
Reloadhttps://patch-diff.githubusercontent.com/ModelTC/SageAttention
Reloadhttps://patch-diff.githubusercontent.com/ModelTC/SageAttention
ModelTC https://patch-diff.githubusercontent.com/ModelTC
SageAttentionhttps://patch-diff.githubusercontent.com/ModelTC/SageAttention
thu-ml/SageAttentionhttps://patch-diff.githubusercontent.com/thu-ml/SageAttention
Notifications https://patch-diff.githubusercontent.com/login?return_to=%2FModelTC%2FSageAttention
Fork 1 https://patch-diff.githubusercontent.com/login?return_to=%2FModelTC%2FSageAttention
Star 2 https://patch-diff.githubusercontent.com/login?return_to=%2FModelTC%2FSageAttention
Apache-2.0 license https://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/LICENSE
2 stars https://patch-diff.githubusercontent.com/ModelTC/SageAttention/stargazers
344 forks https://patch-diff.githubusercontent.com/ModelTC/SageAttention/forks
Branches https://patch-diff.githubusercontent.com/ModelTC/SageAttention/branches
Tags https://patch-diff.githubusercontent.com/ModelTC/SageAttention/tags
Activity https://patch-diff.githubusercontent.com/ModelTC/SageAttention/activity
Star https://patch-diff.githubusercontent.com/login?return_to=%2FModelTC%2FSageAttention
Notifications https://patch-diff.githubusercontent.com/login?return_to=%2FModelTC%2FSageAttention
Code https://patch-diff.githubusercontent.com/ModelTC/SageAttention
Pull requests 1 https://patch-diff.githubusercontent.com/ModelTC/SageAttention/pulls
Actions https://patch-diff.githubusercontent.com/ModelTC/SageAttention/actions
Projects 0 https://patch-diff.githubusercontent.com/ModelTC/SageAttention/projects
Security 0 https://patch-diff.githubusercontent.com/ModelTC/SageAttention/security
Insights https://patch-diff.githubusercontent.com/ModelTC/SageAttention/pulse
Code https://patch-diff.githubusercontent.com/ModelTC/SageAttention
Pull requests https://patch-diff.githubusercontent.com/ModelTC/SageAttention/pulls
Actions https://patch-diff.githubusercontent.com/ModelTC/SageAttention/actions
Projects https://patch-diff.githubusercontent.com/ModelTC/SageAttention/projects
Security https://patch-diff.githubusercontent.com/ModelTC/SageAttention/security
Insights https://patch-diff.githubusercontent.com/ModelTC/SageAttention/pulse
Brancheshttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/branches
Tagshttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/tags
https://patch-diff.githubusercontent.com/ModelTC/SageAttention/branches
https://patch-diff.githubusercontent.com/ModelTC/SageAttention/tags
126 Commitshttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/commits/main/
https://patch-diff.githubusercontent.com/ModelTC/SageAttention/commits/main/
assetshttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/tree/main/assets
assetshttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/tree/main/assets
benchhttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/tree/main/bench
benchhttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/tree/main/bench
csrchttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/tree/main/csrc
csrchttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/tree/main/csrc
examplehttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/tree/main/example
examplehttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/tree/main/example
sageattentionhttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/tree/main/sageattention
sageattentionhttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/tree/main/sageattention
.gitignorehttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/.gitignore
.gitignorehttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/.gitignore
LICENSEhttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/LICENSE
LICENSEhttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/LICENSE
README.mdhttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/README.md
README.mdhttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/README.md
setup.pyhttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/setup.py
setup.pyhttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/setup.py
READMEhttps://patch-diff.githubusercontent.com/ModelTC/SageAttention
Licensehttps://patch-diff.githubusercontent.com/ModelTC/SageAttention
https://patch-diff.githubusercontent.com/ModelTC/SageAttention#sageattention
https://arxiv.org/abs/2410.02367https://arxiv.org/abs/2410.02367
https://arxiv.org/abs/2411.10958https://arxiv.org/abs/2411.10958
https://arxiv.org/abs/2505.11594https://arxiv.org/abs/2505.11594
https://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/assets/2.png
SageAttention2++https://arxiv.org/pdf/2505.21136
https://patch-diff.githubusercontent.com/ModelTC/SageAttention#current-features
https://patch-diff.githubusercontent.com/ModelTC/SageAttention#project-updates
HuggingFacehttps://huggingface.co/jt-zhang/SageAttention3
SageAttention2++https://arxiv.org/pdf/2505.21136
Huggingfacehttps://huggingface.co/jt-zhang/SageAttention2_plus
https://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/assets/5090_sageattn2++.png
https://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/assets/4090_sageattn2++.png
Herehttps://github.com/jt-zhang/Sparse_SageAttention_API
SpargeAttnhttps://github.com/thu-ml/SpargeAttn
SpargeAttnhttps://github.com/thu-ml/SpargeAttn
https://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/assets/cogvideox1.5_fa2_example.gif
https://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/assets/cogvideox1.5_fa3_example.gif
https://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/assets/cogvideox1.5_fa3fp8_example.gif
https://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/assets/cogvideox1.5_sage_example.gif
CogVideoX1.5-5Bhttps://huggingface.co/THUDM/CogVideoX1.5-5B
https://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/assets/H100_hd128.png
https://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/assets/H20_hd128.png
SageAttention2 Paperhttps://arxiv.org/abs/2411.10958
https://patch-diff.githubusercontent.com/ModelTC/SageAttention#installation
https://patch-diff.githubusercontent.com/ModelTC/SageAttention#base-environment
https://patch-diff.githubusercontent.com/ModelTC/SageAttention#install-package
SageAttention-1https://github.com/thu-ml/SageAttention/tree/sageattention-1
https://patch-diff.githubusercontent.com/ModelTC/SageAttention#how-to-use
https://patch-diff.githubusercontent.com/ModelTC/SageAttention#available-apis
this filehttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/sageattention/core.py
https://patch-diff.githubusercontent.com/ModelTC/SageAttention#plug-and-play-example
CogvideoXhttps://huggingface.co/THUDM/CogVideoX-2b
https://patch-diff.githubusercontent.com/ModelTC/SageAttention#kernel-benchmarking
https://patch-diff.githubusercontent.com/ModelTC/SageAttention#performance
https://patch-diff.githubusercontent.com/ModelTC/SageAttention#speed-of-kernels
https://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/assets/5090_sageattn2++.png
https://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/assets/4090_sageattn2++.png
https://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/assets/4090_hd128.png
https://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/assets/L20_hd128.png
https://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/assets/H100_hd128.png
https://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/assets/H20_hd128.png
https://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/assets/A100_hd128.png
https://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/assets/3090_hd128.png
https://patch-diff.githubusercontent.com/ModelTC/SageAttention#end-to-end-performance
https://patch-diff.githubusercontent.com/ModelTC/SageAttention#end-to-end-accuracy
https://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/assets/22.png
https://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/assets/23.png
https://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/assets/24.png
https://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/assets/25.png
https://patch-diff.githubusercontent.com/ModelTC/SageAttention#end-to-end-speedup
https://patch-diff.githubusercontent.com/ModelTC/SageAttention/blob/main/assets/26.png
https://patch-diff.githubusercontent.com/ModelTC/SageAttention#citation
Readme https://patch-diff.githubusercontent.com/ModelTC/SageAttention#readme-ov-file
Apache-2.0 license https://patch-diff.githubusercontent.com/ModelTC/SageAttention#Apache-2.0-1-ov-file
Please reload this pagehttps://patch-diff.githubusercontent.com/ModelTC/SageAttention
Activityhttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/activity
Custom propertieshttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/custom-properties
2 starshttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/stargazers
0 watchinghttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/watchers
1 forkhttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/forks
Report repository https://patch-diff.githubusercontent.com/contact/report-content?content_url=https%3A%2F%2Fgithub.com%2FModelTC%2FSageAttention&report=ModelTC+%28user%29
Releaseshttps://patch-diff.githubusercontent.com/ModelTC/SageAttention/releases
Packages 0https://patch-diff.githubusercontent.com/orgs/ModelTC/packages?repo_name=SageAttention
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.