Skip to content

Conversation

@suexu1025
Copy link
Collaborator

@suexu1025 suexu1025 commented Nov 14, 2025

Description

  • add flag to enable tokamax attention scheduler for better overlap communication and compute.

If the change fixes a bug or a Github issue, please include a link, e.g.,:
FIXES: b/123456
FIXES: #123456

Notice 1: Once all tests pass, the "pull ready" label will automatically be assigned.
This label is used for administrative purposes. Please do not add it manually.

Notice 2: For external contributions, our settings currently require an approval from a MaxText maintainer to trigger CI tests.

Tests

Please describe how you tested this change, and include any instructions and/or
commands to reproduce.

Checklist

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

  • I have performed a self-review of my code. For an optional AI review, add the gemini-review label.
  • 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, including adding new documentation pages to the relevant Table of Contents (toctree directive) as explained in our documentation.

Copy link
Collaborator

@RissyRan RissyRan left a comment

Choose a reason for hiding this comment

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

Thanks!

cost_estimate_flops_fwd: -1 # -1 means using splash default cost estmiation, any >= 0 value will be used as cost estmiation for splash to overlap for communication (forward)
cost_estimate_flops_bwd: -1 # -1 means using splash default cost estmiation, any >= 0 value will be used as cost estmiation for splash to overlap for communication (backward)
dq_reduction_steps: 0 #the number of reduction steps. For now, only 3 or all the kv steps are supported.
use_splash_scheduler: false # to use tokamax splash attention scheduler.
Copy link
Collaborator

Choose a reason for hiding this comment

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

Nit: False for alignment

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants