mps: Alternative implementation for repeat_interleave
#766
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
The documentation is not available anymore as the PR was closed or merged. |
patil-suraj
reviewed
Oct 7, 2022
Contributor
patil-suraj
left a comment
patil-suraj
left a comment
There was a problem hiding this comment.
Looks good, just left couple of comments.
src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py
Outdated
Show resolved
Hide resolved
src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py
Outdated
Show resolved
Hide resolved
src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py
Outdated
Show resolved
Hide resolved
src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py
Outdated
Show resolved
Hide resolved
Co-authored-by: Suraj Patil <[email protected]>
Member
Author
|
Changes applied, I think this is ready to go @patil-suraj @patrickvonplaten |
Member
Author
|
Hmm, the test is failing, I'll verify it locally. |
patil-suraj
approved these changes
Oct 10, 2022
Contributor
patil-suraj
left a comment
patil-suraj
left a comment
There was a problem hiding this comment.
Good to merge for me once the tests pass.
src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py
Outdated
Show resolved
Hide resolved
src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py
Outdated
Show resolved
Hide resolved
patrickvonplaten
approved these changes
Oct 11, 2022
- The unconditional embeddings are always created from a single prompt. - I was shadowing the batch_size var.
patrickvonplaten
added a commit
that referenced
this pull request
Oct 11, 2022
* mps: alt. implementation for repeat_interleave * style * Bump mps version of PyTorch in the documentation. * Apply suggestions from code review Co-authored-by: Suraj Patil <[email protected]> * Simplify: do not check for device. * style * Fix repeat dimensions: - The unconditional embeddings are always created from a single prompt. - I was shadowing the batch_size var. * Split long lines as suggested by Suraj. Co-authored-by: Patrick von Platen <[email protected]> Co-authored-by: Suraj Patil <[email protected]>
prathikr
pushed a commit
to prathikr/diffusers
that referenced
this pull request
Oct 26, 2022
…e#766) * mps: alt. implementation for repeat_interleave * style * Bump mps version of PyTorch in the documentation. * Apply suggestions from code review Co-authored-by: Suraj Patil <[email protected]> * Simplify: do not check for device. * style * Fix repeat dimensions: - The unconditional embeddings are always created from a single prompt. - I was shadowing the batch_size var. * Split long lines as suggested by Suraj. Co-authored-by: Patrick von Platen <[email protected]> Co-authored-by: Suraj Patil <[email protected]>
yoonseokjin
pushed a commit
to yoonseokjin/diffusers
that referenced
this pull request
Dec 25, 2023
…e#766) * mps: alt. implementation for repeat_interleave * style * Bump mps version of PyTorch in the documentation. * Apply suggestions from code review Co-authored-by: Suraj Patil <[email protected]> * Simplify: do not check for device. * style * Fix repeat dimensions: - The unconditional embeddings are always created from a single prompt. - I was shadowing the batch_size var. * Split long lines as suggested by Suraj. Co-authored-by: Patrick von Platen <[email protected]> Co-authored-by: Suraj Patil <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Fixes #760.
repeat_interleavewas slowing things down, but not causing wrong outputs. Something betweenv0.3.0andv0.4.0(possibly some of the optimization changes) broke generation inmps. Fortunately, the latestmpsversion of PyTorch nightly (released today) works fine 😅, so I'm updating the documentation to recommend it.