Skip to content

Support weight sharing in PTE #13941

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 15 commits into from
Sep 8, 2025
Merged

Support weight sharing in PTE #13941

merged 15 commits into from
Sep 8, 2025

Conversation

neuropilot-captain
Copy link
Collaborator

Summary

  1. Support weight sharing with compile spec
  2. Support weight sharing feature to llama export script and runner
  3. Optimize llama performance

@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Sep 4, 2025 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/13941

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

❌ 3 New Failures

As of commit 6b30094 with merge base b02db12 (image):

NEW FAILURES - The following jobs have failed:

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

@meta-cla meta-cla 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 Sep 4, 2025
@github-actions GitHub Actions
Copy link

github-actions bot commented Sep 4, 2025

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

@cccclai
Copy link
Contributor

cccclai commented Sep 4, 2025

@neuropilot-captain I think the PR needs to rebase

@cccclai
Copy link
Contributor

cccclai commented Sep 5, 2025

There is still lint error...can you fix it?

@cccclai cccclai merged commit a90e907 into pytorch:main Sep 8, 2025
113 of 116 checks passed
swolchok
swolchok reviewed Sep 9, 2025
View reviewed changes
examples/mediatek/executor_runner/llama_runner/ModelChunk.cpp
Comment on lines +156 to +157
mPlannedBuffers.push_back(std::make_unique<uint8_t[]>(buffer_size));
mPlannedSpans.push_back({mPlannedBuffers.back().get(), buffer_size});
Copy link
Contributor

Choose a reason for hiding this comment

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

nit: use emplace_back

examples/mediatek/executor_runner/llama_runner/ModelChunk.cpp
ET_LOG(Debug, "Setting up planned buffer %zu, size %zu.", id, buffer_size);
planned_buffers.push_back(std::make_unique<uint8_t[]>(buffer_size));
planned_spans.push_back({planned_buffers.back().get(), buffer_size});
auto modelInstance = new ModelInstance(modelPath);
Copy link
Contributor

Choose a reason for hiding this comment

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

use unique_ptr; this will leak if anything in here throws

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

@swolchok swolchok swolchok left review comments

@cccclai cccclai cccclai approved these changes

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.
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@neuropilot-captain @cccclai @swolchok