Skip to content

Fix Gemma3 and Gemma2 flops computation.#2009

Merged
copybara-service[bot] merged 1 commit into
mainfrom
gemma3-flops
Jul 23, 2025
Merged

Fix Gemma3 and Gemma2 flops computation.#2009
copybara-service[bot] merged 1 commit into
mainfrom
gemma3-flops

Conversation

@gagika

@gagika gagika commented Jul 22, 2025

Copy link
Copy Markdown
Collaborator

Description

  • Add correct local attention flops for Gemma3
  • Change both gemma2 and gemma3 to use causal attention flops (total attention flops / 2).

Checklist

Before submitting this PR, please make sure (put X in square brackets):

  • I have performed a self-review of my code.
  • I have necessary comments in my code, particularly in hard-to-understand areas.
  • I have run end-to-end tests tests and provided workload links above if applicable.
  • I have made or will make corresponding changes to the doc if needed.

@gagika
gagika force-pushed the gemma3-flops branch 2 times, most recently from a72f72d to 4760e6a Compare July 22, 2025 20:29
@gagika
gagika marked this pull request as ready for review July 22, 2025 20:50
gobbleturk
gobbleturk approved these changes Jul 23, 2025
View reviewed changes

@gobbleturk gobbleturk left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks gagik!

@copybara-service
copybara-service Bot merged commit 6da8ede into main Jul 23, 2025
20 checks passed
@copybara-service
copybara-service Bot deleted the gemma3-flops branch July 23, 2025 19:42
This was referenced Aug 1, 2025
Open
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@gobbleturk gobbleturk gobbleturk approved these changes
@bvandermoon bvandermoon bvandermoon approved these changes
@khatwanimohit khatwanimohit Awaiting requested review from khatwanimohit khatwanimohit is a code owner
@vipannalla vipannalla Awaiting requested review from vipannalla vipannalla is a code owner
@RissyRan RissyRan Awaiting requested review from RissyRan RissyRan is a code owner
@richjames0 richjames0 Awaiting requested review from richjames0 richjames0 is a code owner
@shralex shralex Awaiting requested review from shralex shralex is a code owner
@yangyuwei yangyuwei Awaiting requested review from yangyuwei
@SurbhiJainUSC SurbhiJainUSC Awaiting requested review from SurbhiJainUSC SurbhiJainUSC is a code owner
@hengtaoguo hengtaoguo Awaiting requested review from hengtaoguo hengtaoguo is a code owner
@A9isha A9isha Awaiting requested review from A9isha A9isha is a code owner
@aireenmei aireenmei Awaiting requested review from aireenmei aireenmei is a code owner
@lukebaumann lukebaumann Awaiting requested review from lukebaumann
@shauryagup shauryagup Awaiting requested review from shauryagup
@RoshaniN RoshaniN Awaiting requested review from RoshaniN
@michelle-yooh michelle-yooh Awaiting requested review from michelle-yooh

Assignees

@gobbleturk gobbleturk

@NuojCheng NuojCheng

Labels

pull ready

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@gagika @gobbleturk @bvandermoon @NuojCheng