Skip to content

Qualcomm AI Engine Direct - Refine max spill fill buffer setting #6041

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 1 commit into from
Oct 9, 2024
Merged

Qualcomm AI Engine Direct - Refine max spill fill buffer setting #6041

merged 1 commit into from
Oct 9, 2024

Conversation

pytorchbot
Copy link
Collaborator

  • Get required spillFillBufferSize from context binary and set to compiler_spec
  • Quantize embedding op in qnn.
  • If enable multi-contexts, maxSpillFillBuffer could not set to zero.

@pytorchbot
Qualcomm AI Engine Direct - Refine max spill fill buffer setting (#5989)
cd8de14 
Summary:
- Get required spillFillBufferSize from context binary and set to compiler_spec
- Quantize embedding op in qnn.
- If enable multi-contexts, maxSpillFillBuffer could not set to zero.

Pull Request resolved: #5989

Reviewed By: kirklandsign

Differential Revision: D64056107

Pulled By: cccclai

fbshipit-source-id: 9f9846e6ac7b4a27d734d2812ac3bbad32fb194f
(cherry picked from commit 01fcdf4)
This was referenced Oct 9, 2024
Closed
Closed
@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Oct 9, 2024 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/6041

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

✅ No Failures

As of commit cd8de14 with merge base eecf74f (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 Oct 9, 2024
jackzhxng
jackzhxng reviewed Oct 9, 2024
View reviewed changes
Copy link
Contributor

@jackzhxng jackzhxng left a comment

Choose a reason for hiding this comment

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

Reason for CP

  • Reduces memory used by 4GB (12 -> 8)
  • Minimal risk, since all changes are QNN related
    • export_llama_lib, partitioner_lib, and quantizer_lib are all gated by qnn arg

Looks good but please fix the one failing test!

jackzhxng
jackzhxng approved these changes Oct 9, 2024
View reviewed changes
Copy link
Contributor

@jackzhxng jackzhxng left a comment •
edited
Loading

Choose a reason for hiding this comment

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

Update: I was looking elsewhere, CI is actually green

@jackzhxng jackzhxng merged commit b73fb1e into release/0.4 Oct 9, 2024
34 checks passed
@jackzhxng jackzhxng deleted the cherry-pick-5989-by-pytorch_bot_bot_ branch October 9, 2024 17:10
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@jackzhxng jackzhxng jackzhxng 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
@pytorchbot @jackzhxng @facebook-github-bot