Skip to content
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

Added experimental mm padding for cache behavior #825

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Added experimental mm padding for cache behavior #825

wants to merge 1 commit into from
+170 −7

Conversation

rsuderman
Copy link
Contributor

Padding to cache lines can significantly improve performance by separating out cache lines between iterations.

@rsuderman
Added experimental mm padding for cache behavior
b630c33 
Padding to cache lines can significantly improve performance by
separating out cache lines between iterations.
@rsuderman
Copy link
Contributor Author

Include sample invocation:

python3 -m sharktank.examples.export_paged_llm_v1 --block-seq-stride=32 --attention-kernel=torch --bs=4 --irpa-file irpa/llama.8b.fp16.irpa --output-mlir /tmp/llama.mlir --experimental-mm-cache-size=128 --^Cperimental-mm-cache-s
ets=4

=

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@rsuderman