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

support ET dump for llama3 runner #7507

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

support ET dump for llama3 runner #7507

wants to merge 1 commit into from
+70 −5

Conversation

billmguo
Copy link

@billmguo billmguo commented Jan 3, 2025

Summary: Support ET dump for llama3 runner to easy understand the regression performance issue

Differential Revision: D67656207

@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Jan 3, 2025 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/7507

Note: Links to docs will display an error until the docs builds have been completed.

✅ No Failures

As of commit 25db0b5 with merge base 54f0786 (image):
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Jan 3, 2025
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D67656207

billmguo added a commit to billmguo/executorch that referenced this pull request Jan 6, 2025
@billmguo @facebook-github-bot
support ET dump for llama3 runner (pytorch#7507)
83e01d8 
Summary:

Support ET dump for llama3 runner to easy understand the regression performance issue

Differential Revision: D67656207
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D67656207

billmguo added a commit to billmguo/executorch that referenced this pull request Jan 6, 2025
@billmguo @facebook-github-bot
support ET dump for llama3 runner (pytorch#7507)
acdefd9 
Summary:

Support ET dump for llama3 runner to easy understand the regression performance issue

Reviewed By: Andriyluck, limintang

Differential Revision: D67656207
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D67656207

haowhsu-quic
haowhsu-quic reviewed Jan 7, 2025
View reviewed changes
examples/qualcomm/oss_scripts/llama3_2/runner/runner.cpp Outdated
gen_etdump_ = true;
switch(eval_mode) {
case EvalMode::kPrefill:
prefill_dump_ = new torch::executor::ETDumpGen();
Copy link
Collaborator

Choose a reason for hiding this comment

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

Maybe use smart pointer to take care of life cycle.

Copy link
Author

Choose a reason for hiding this comment

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

update the diff with smart pointer

billmguo added a commit to billmguo/executorch that referenced this pull request Jan 7, 2025
@billmguo @facebook-github-bot
support ET dump for llama3 runner (pytorch#7507)
541ef6c 
Summary:

Support ET dump for llama3 runner to easy understand the regression performance issue

Reviewed By: Andriyluck, limintang

Differential Revision: D67656207
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D67656207

billmguo added a commit to billmguo/executorch that referenced this pull request Jan 8, 2025
@billmguo @facebook-github-bot
support ET dump for llama3 runner (pytorch#7507)
1123e3f 
Summary:

Support ET dump for llama3 runner to easy understand the regression performance issue

Reviewed By: Andriyluck, limintang

Differential Revision: D67656207
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D67656207

@billmguo @facebook-github-bot
support ET dump for llama3 runner (pytorch#7507)
25db0b5 
Summary:

Support ET dump for llama3 runner to easy understand the regression performance issue

Reviewed By: Andriyluck, limintang

Differential Revision: D67656207
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D67656207

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

@haowhsu-quic haowhsu-quic haowhsu-quic left review comments

@cccclai cccclai cccclai left review comments

@limintang limintang limintang approved these changes

@chunit-quic chunit-quic Awaiting requested review from chunit-quic

@winskuo-quic winskuo-quic Awaiting requested review from winskuo-quic

@shewu-quic shewu-quic Awaiting requested review from shewu-quic

Assignees
No one assigned
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. fb-exported topic: not user facing
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
5 participants
@billmguo @facebook-github-bot @limintang @cccclai @haowhsu-quic