Upgrade optimum-habana diffusers dependency from 0.26.3 to 0.29.2 #1150
Conversation
This file contains 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
dsocek
force-pushed
the
diffusers-0.29.2-upgrade
branch
from
27ff798 to
da20428
Compare
Merged
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
regisss
reviewed
Aug 2, 2024
dsocek
force-pushed
the
diffusers-0.29.2-upgrade
branch
4 times, most recently
from
4ab70de to
9d115fd
Compare
* Update optimum-habana diffusers to 0.29.2 in setup.py * Fix SVD (GaudiStableVideoDiffusionPipeline) to handle updated API for tensor2vid * Fix GaudiStableDiffusionControlNetPipeline to handle updated check_inputs API * Fix tests/test_diffusers.py to use to(dtype=...) instead of to(torch_dtype=...) which is now deprecated * Clean-up SVD to remove all inheritable functions * Updated warmup logic in SVD * Updated documentation example with command line for SVD that yields improved performace Signed-off-by: Daniel Socek <daniel.socek@intel.com>
regisss
approved these changes
Aug 4, 2024
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Outdated suggestions cannot be applied.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.
Upgrade optimum-habana diffusers from 0.26.3 to 0.29.2
setup.pytensor2vidand instead usevideo_processor.postprocess_videocheck_inputsAPI in 0.29.2tests/test_diffusers.pyto useto(dtype=...)instead ofto(torch_dtype=...)which is deprecated starting diffusers 0.27.0 (See here)Tests
Ran tests on G2:
Diffusers test results before diffusers upgrade:
17 failed, 106 passed, 13 skipped, 65 warnings in 2304.15s (0:38:24)Diffusers test results after diffusers upgrade:
16 failed, 107 passed, 13 skipped, 316 warnings in 2157.94s (0:35:57)Note: Update is needed for supporting enabling newest pipelines such as Stable Diffusion 3, etc.