Skip to content

Use new tuned table #9041

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 3 commits into from
Apr 28, 2025
Merged

Use new tuned table #9041

merged 3 commits into from
Apr 28, 2025

Conversation

bythew3i
Copy link
Contributor

Tested:

python test/test_pallas.py -v -k PallasTest.test_ragged_paged_attention_wrapper_with_dynamo

Taking new factors into account for auto tunning:

  • q_dtype_name
  • kv_dtype_name
  • num_q_heads_per_blk
  • num_kv_heads_per_blk
  • head_dim
  • page_size
  • max_num_batched_tokens
  • max_model_len = page_size * pages_per_seq

@bythew3i
Copy link
Contributor Author

@vanbasten23 @lsy323 @yarongmu-google

@bythew3i
Copy link
Contributor Author

@bvrockwell

@bythew3i bythew3i mentioned this pull request Apr 25, 2025
Merged
yaochengji
yaochengji approved these changes Apr 28, 2025
View reviewed changes
Copy link
Collaborator

@yaochengji yaochengji left a comment

Choose a reason for hiding this comment

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

LGTM, thanks for your great contribution!

@yaochengji yaochengji merged commit c4b45a9 into pytorch:master Apr 28, 2025
45 of 46 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@yaochengji yaochengji yaochengji approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@bythew3i @yaochengji