René's URL Explorer Experiment


Title: Fix Llama4 attention flops by gagika · Pull Request #2030 · AI-Hypercomputer/maxtext · GitHub

Open Graph Title: Fix Llama4 attention flops by gagika · Pull Request #2030 · AI-Hypercomputer/maxtext

X Title: Fix Llama4 attention flops by gagika · Pull Request #2030 · AI-Hypercomputer/maxtext

Description: Description Fix Llama4 attention flops to only count for chunk attention window size for chunk attention layers. Tests Comparing total_tflops, learnable_weight_tflops, attention_tflops before and a...

Open Graph Description: Description Fix Llama4 attention flops to only count for chunk attention window size for chunk attention layers. Tests Comparing total_tflops, learnable_weight_tflops, attention_tflops before and a...

X Description: Description Fix Llama4 attention flops to only count for chunk attention window size for chunk attention layers. Tests Comparing total_tflops, learnable_weight_tflops, attention_tflops before and a...

Opengraph URL: https://github.com/AI-Hypercomputer/maxtext/pull/2030

X: @github

direct link

Domain: github.com

route-pattern/_view_fragments/voltron/pull_requests/show/:user_id/:repository/:id/pull_request_layout(.:format)
route-controllervoltron_pull_requests_fragments
route-actionpull_request_layout
fetch-noncev2:cea71ec4-45a4-757b-a684-224b8a938a35
current-catalog-service-hashae870bc5e265a340912cde392f23dad3671a0a881730ffdadd82f2f57d81641b
request-idCEAE:314667:949D06:C02AE4:69644324
html-safe-nonced482847977bf5c542e90ac1415d59e51ddebd2e64ef723c643d58f54528c640c
visitor-payloadeyJyZWZlcnJlciI6IiIsInJlcXVlc3RfaWQiOiJDRUFFOjMxNDY2Nzo5NDlEMDY6QzAyQUU0OjY5NjQ0MzI0IiwidmlzaXRvcl9pZCI6IjMyNzM1NjY2NjM5NTE1MzI4MzYiLCJyZWdpb25fZWRnZSI6ImlhZCIsInJlZ2lvbl9yZW5kZXIiOiJpYWQifQ==
visitor-hmac1a4753934aae2b917f9562036db3d5b25be3decaade732dbf08f0a5a81208991
hovercard-subject-tagpull_request:2696340294
github-keyboard-shortcutsrepository,pull-request-list,pull-request-conversation,pull-request-files-changed,copilot
google-site-verificationApib7-x98H0j5cPqHWwSMm6dNU4GmODRoqxLiDzdx9I
octolytics-urlhttps://collector.github.com/github/collect
analytics-location///voltron/pull_requests_fragments/pull_request_layout
fb:app_id1401488693436528
apple-itunes-appapp-id=1477376905, app-argument=https://github.com/_view_fragments/voltron/pull_requests/show/AI-Hypercomputer/maxtext/2030/pull_request_layout
twitter:imagehttps://opengraph.githubassets.com/b03fa2f730c968c10346a06e61e3c1fbc4e6dfc4fb6d9a4419ab9b80b611fbb8/AI-Hypercomputer/maxtext/pull/2030
twitter:cardsummary_large_image
og:imagehttps://opengraph.githubassets.com/b03fa2f730c968c10346a06e61e3c1fbc4e6dfc4fb6d9a4419ab9b80b611fbb8/AI-Hypercomputer/maxtext/pull/2030
og:image:altDescription Fix Llama4 attention flops to only count for chunk attention window size for chunk attention layers. Tests Comparing total_tflops, learnable_weight_tflops, attention_tflops before and a...
og:image:width1200
og:image:height600
og:site_nameGitHub
og:typeobject
og:author:usernamegagika
hostnamegithub.com
expected-hostnamegithub.com
Nonebaa7d9900fdf7b27d604f36887af878d569cfbdcf97126832a5f4f0caf0c6ba5
turbo-cache-controlno-preview
go-importgithub.com/AI-Hypercomputer/maxtext git https://github.com/AI-Hypercomputer/maxtext.git
octolytics-dimension-user_id181000646
octolytics-dimension-user_loginAI-Hypercomputer
octolytics-dimension-repository_id607845880
octolytics-dimension-repository_nwoAI-Hypercomputer/maxtext
octolytics-dimension-repository_publictrue
octolytics-dimension-repository_is_forkfalse
octolytics-dimension-repository_network_root_id607845880
octolytics-dimension-repository_network_root_nwoAI-Hypercomputer/maxtext
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
release842eff1d11f899d02b6b3b98fa3ea4860e64b34e
ui-targetfull
theme-color#1e2327
color-schemelight dark

Links:

Skip to contenthttps://github.com/AI-Hypercomputer/maxtext/pull/2030#start-of-content
https://github.com/
Sign in https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2FAI-Hypercomputer%2Fmaxtext%2Fpull%2F2030
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://github.com/login?return_to=https%3A%2F%2Fgithub.com%2FAI-Hypercomputer%2Fmaxtext%2Fpull%2F2030
Sign up https://github.com/signup?ref_cta=Sign+up&ref_loc=header+logged+out&ref_page=%2F%3Cuser-name%3E%2F%3Crepo-name%3E%2Fvoltron%2Fpull_requests_fragments%2Fpull_request_layout&source=header-repo&source_repo=AI-Hypercomputer%2Fmaxtext
Reloadhttps://github.com/AI-Hypercomputer/maxtext/pull/2030
Reloadhttps://github.com/AI-Hypercomputer/maxtext/pull/2030
Reloadhttps://github.com/AI-Hypercomputer/maxtext/pull/2030
AI-Hypercomputer https://github.com/AI-Hypercomputer
maxtexthttps://github.com/AI-Hypercomputer/maxtext
Notifications https://github.com/login?return_to=%2FAI-Hypercomputer%2Fmaxtext
Fork 447 https://github.com/login?return_to=%2FAI-Hypercomputer%2Fmaxtext
Star 2.1k https://github.com/login?return_to=%2FAI-Hypercomputer%2Fmaxtext
Code https://github.com/AI-Hypercomputer/maxtext
Issues 76 https://github.com/AI-Hypercomputer/maxtext/issues
Pull requests 179 https://github.com/AI-Hypercomputer/maxtext/pulls
Actions https://github.com/AI-Hypercomputer/maxtext/actions
Projects 0 https://github.com/AI-Hypercomputer/maxtext/projects
Security Uh oh! There was an error while loading. Please reload this page. https://github.com/AI-Hypercomputer/maxtext/security
Please reload this pagehttps://github.com/AI-Hypercomputer/maxtext/pull/2030
Insights https://github.com/AI-Hypercomputer/maxtext/pulse
Code https://github.com/AI-Hypercomputer/maxtext
Issues https://github.com/AI-Hypercomputer/maxtext/issues
Pull requests https://github.com/AI-Hypercomputer/maxtext/pulls
Actions https://github.com/AI-Hypercomputer/maxtext/actions
Projects https://github.com/AI-Hypercomputer/maxtext/projects
Security https://github.com/AI-Hypercomputer/maxtext/security
Insights https://github.com/AI-Hypercomputer/maxtext/pulse
Sign up for GitHub https://github.com/signup?return_to=%2FAI-Hypercomputer%2Fmaxtext%2Fissues%2Fnew%2Fchoose
terms of servicehttps://docs.github.com/terms
privacy statementhttps://docs.github.com/privacy
Sign inhttps://github.com/login?return_to=%2FAI-Hypercomputer%2Fmaxtext%2Fissues%2Fnew%2Fchoose
Jump to bottomhttps://github.com/AI-Hypercomputer/maxtext/pull/2030#issue-comment-box
copybara-servicehttps://github.com/apps/copybara-service
mainhttps://github.com/AI-Hypercomputer/maxtext/tree/main
llama4-flopshttps://github.com/AI-Hypercomputer/maxtext/tree/llama4-flops
Fix Llama4 attention flops https://github.com/AI-Hypercomputer/maxtext/pull/2030#top
copybara-servicehttps://github.com/apps/copybara-service
mainhttps://github.com/AI-Hypercomputer/maxtext/tree/main
llama4-flopshttps://github.com/AI-Hypercomputer/maxtext/tree/llama4-flops
Conversation 4 https://github.com/AI-Hypercomputer/maxtext/pull/2030
Commits 1 https://github.com/AI-Hypercomputer/maxtext/pull/2030/commits
Checks 17 https://github.com/AI-Hypercomputer/maxtext/pull/2030/checks
Files changed https://github.com/AI-Hypercomputer/maxtext/pull/2030/files
Please reload this pagehttps://github.com/AI-Hypercomputer/maxtext/pull/2030
https://github.co/hiddenchars
https://github.com/AI-Hypercomputer/maxtext/pull/{{ revealButtonHref }}
https://github.com/gagika
gagikahttps://github.com/gagika
Jul 26, 2025https://github.com/AI-Hypercomputer/maxtext/pull/2030#issue-3264801030
Please reload this pagehttps://github.com/AI-Hypercomputer/maxtext/pull/2030
https://diff.googleplex.com/#key=wo0bVmy9wbUchttps://diff.googleplex.com/#key=wo0bVmy9wbUc
Please reload this pagehttps://github.com/AI-Hypercomputer/maxtext/pull/2030
https://github.com/gagika
gagikahttps://github.com/gagika
July 27, 2025 19:39https://github.com/AI-Hypercomputer/maxtext/pull/2030#event-18841348031
https://github.com/gagika
gagikahttps://github.com/gagika
A9ishahttps://github.com/A9isha
RissyRanhttps://github.com/RissyRan
SurbhiJainUSChttps://github.com/SurbhiJainUSC
aireenmeihttps://github.com/aireenmei
bvandermoonhttps://github.com/bvandermoon
gobbleturkhttps://github.com/gobbleturk
hengtaoguohttps://github.com/hengtaoguo
khatwanimohithttps://github.com/khatwanimohit
richjames0https://github.com/richjames0
shralexhttps://github.com/shralex
vipannallahttps://github.com/vipannalla
yangyuweihttps://github.com/yangyuwei
code ownershttps://github.com/AI-Hypercomputer/maxtext/blob/e969faabbb571285a51545530f34d8f0a9f237e9/.github/CODEOWNERS#L1
July 27, 2025 19:39https://github.com/AI-Hypercomputer/maxtext/pull/2030#event-18841348071
https://github.com/gagika
gagikahttps://github.com/gagika
gobbleturkhttps://github.com/gobbleturk
shralexhttps://github.com/shralex
NuojChenghttps://github.com/NuojCheng
Jul 27, 2025https://github.com/AI-Hypercomputer/maxtext/pull/2030#event-18841348538
https://github.com/RissyRan
RissyRanhttps://github.com/RissyRan
Jul 28, 2025 https://github.com/AI-Hypercomputer/maxtext/pull/2030#pullrequestreview-3063996948
View reviewed changes https://github.com/AI-Hypercomputer/maxtext/pull/2030/files
RissyRanhttps://github.com/RissyRan
https://github.com/AI-Hypercomputer/maxtext/pull/2030#pullrequestreview-3063996948
Learn morehttps://docs.github.com/articles/managing-disruptive-comments/#hiding-a-comment
Please reload this pagehttps://github.com/AI-Hypercomputer/maxtext/pull/2030
https://github.com/gobbleturk
gobbleturkhttps://github.com/gobbleturk
Jul 28, 2025 https://github.com/AI-Hypercomputer/maxtext/pull/2030#pullrequestreview-3064093521
View reviewed changes https://github.com/AI-Hypercomputer/maxtext/pull/2030/files
MaxText/maxtext_utils.pyhttps://github.com/AI-Hypercomputer/maxtext/pull/2030/files#diff-42b892aaeaab0d6e847530e0399cf0c215fa17efddfdbbe09b69a1c043f57c1f
gobbleturkhttps://github.com/gobbleturk
Jul 28, 2025https://github.com/AI-Hypercomputer/maxtext/pull/2030#discussion_r2237490272
Learn morehttps://docs.github.com/articles/managing-disruptive-comments/#hiding-a-comment
Please reload this pagehttps://github.com/AI-Hypercomputer/maxtext/pull/2030
gagikahttps://github.com/gagika
Jul 28, 2025https://github.com/AI-Hypercomputer/maxtext/pull/2030#discussion_r2237687822
Learn morehttps://docs.github.com/articles/managing-disruptive-comments/#hiding-a-comment
Please reload this pagehttps://github.com/AI-Hypercomputer/maxtext/pull/2030
https://github.com/gobbleturk
gobbleturkhttps://github.com/gobbleturk
Jul 28, 2025 https://github.com/AI-Hypercomputer/maxtext/pull/2030#pullrequestreview-3064094682
View reviewed changes https://github.com/AI-Hypercomputer/maxtext/pull/2030/files
gobbleturkhttps://github.com/gobbleturk
https://github.com/AI-Hypercomputer/maxtext/pull/2030#pullrequestreview-3064094682
Learn morehttps://docs.github.com/articles/managing-disruptive-comments/#hiding-a-comment
Please reload this pagehttps://github.com/AI-Hypercomputer/maxtext/pull/2030
https://github.com/apps/github-actions
github-actionshttps://github.com/apps/github-actions
pull ready https://github.com/AI-Hypercomputer/maxtext/issues?q=state%3Aopen%20label%3A%22pull%20ready%22
Jul 28, 2025https://github.com/AI-Hypercomputer/maxtext/pull/2030#event-18862095054
https://github.com/gagika
Fix Llama4 attention flopshttps://github.com/AI-Hypercomputer/maxtext/pull/2030/commits/43f5406c4fff2b1c9f694f513b8874b0fab75efd
43f5406https://github.com/AI-Hypercomputer/maxtext/pull/2030/commits/43f5406c4fff2b1c9f694f513b8874b0fab75efd
https://github.com/gagika
gagikahttps://github.com/gagika
force-pushedhttps://github.com/AI-Hypercomputer/maxtext/compare/22d6db6867a473345232962eb11c049c2cb2be26..43f5406c4fff2b1c9f694f513b8874b0fab75efd
22d6db6https://github.com/AI-Hypercomputer/maxtext/commit/22d6db6867a473345232962eb11c049c2cb2be26
43f5406https://github.com/AI-Hypercomputer/maxtext/commit/43f5406c4fff2b1c9f694f513b8874b0fab75efd
Compare https://github.com/AI-Hypercomputer/maxtext/compare/22d6db6867a473345232962eb11c049c2cb2be26..43f5406c4fff2b1c9f694f513b8874b0fab75efd
July 28, 2025 19:36https://github.com/AI-Hypercomputer/maxtext/pull/2030#event-18863401036
https://github.com/apps/copybara-service
copybara-servicehttps://github.com/apps/copybara-service
9cabaf6https://github.com/AI-Hypercomputer/maxtext/commit/9cabaf63730840242fbf689327e8c6663f660c23
Jul 28, 2025https://github.com/AI-Hypercomputer/maxtext/pull/2030#event-18865423759
Please reload this pagehttps://github.com/AI-Hypercomputer/maxtext/pull/2030
https://github.com/apps/copybara-service
copybara-servicehttps://github.com/apps/copybara-service
July 28, 2025 22:35https://github.com/AI-Hypercomputer/maxtext/pull/2030#event-18865423847
[BUG] Inaccurate FLOPs Calculation for Causal and Specialized Attention NVIDIA-NeMo/NeMo#14376 https://github.com/NVIDIA-NeMo/NeMo/issues/14376
[BUG] Inaccurate FLOPs Calculation for Models with Specialized Attention NVIDIA/Megatron-LM#1725 https://github.com/NVIDIA/Megatron-LM/issues/1725
Attention flops calculation doesn't reflect causal masking #1972 https://github.com/AI-Hypercomputer/maxtext/issues/1972
Sign up for freehttps://github.com/join?source=comment-repo
Sign in to commenthttps://github.com/login?return_to=https%3A%2F%2Fgithub.com%2FAI-Hypercomputer%2Fmaxtext%2Fpull%2F2030
https://github.com/RissyRan
RissyRan https://github.com/RissyRan
https://github.com/AI-Hypercomputer/maxtext/pull/2030/files/22d6db6867a473345232962eb11c049c2cb2be26
https://github.com/gobbleturk
gobbleturk https://github.com/gobbleturk
https://github.com/AI-Hypercomputer/maxtext/pull/2030/files/22d6db6867a473345232962eb11c049c2cb2be26
https://github.com/khatwanimohit
khatwanimohit https://github.com/khatwanimohit
https://github.com/bvandermoon
bvandermoon https://github.com/bvandermoon
https://github.com/vipannalla
vipannalla https://github.com/vipannalla
https://github.com/richjames0
richjames0 https://github.com/richjames0
https://github.com/shralex
shralex https://github.com/shralex
https://github.com/yangyuwei
yangyuwei https://github.com/yangyuwei
https://github.com/SurbhiJainUSC
SurbhiJainUSC https://github.com/SurbhiJainUSC
https://github.com/hengtaoguo
hengtaoguo https://github.com/hengtaoguo
https://github.com/A9isha
A9isha https://github.com/A9isha
https://github.com/aireenmei
aireenmei https://github.com/aireenmei
https://github.com/shralex
shralex https://github.com/shralex
https://github.com/gobbleturk
gobbleturk https://github.com/gobbleturk
https://github.com/NuojCheng
NuojCheng https://github.com/NuojCheng
pull ready https://github.com/AI-Hypercomputer/maxtext/issues?q=state%3Aopen%20label%3A%22pull%20ready%22
Please reload this pagehttps://github.com/AI-Hypercomputer/maxtext/pull/2030
https://github.com/gagika
https://github.com/RissyRan
https://github.com/gobbleturk
https://github.com/shralex
https://github.com/NuojCheng
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.