Diffusers support #604
Open
Diffusers support #604
+3,086
−150
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
quic-amitraj
force-pushed
the
config_support_diffusers
branch
5 times, most recently
from
ffed450 to
eb55c51
Compare
quic-amitraj
requested review from
ochougul,
quic-hemagnih and
quic-rishinr
as code owners
quic-amitraj
force-pushed
the
config_support_diffusers
branch
2 times, most recently
from
42cf8b6 to
1cf4b30
Compare
quic-amitraj
force-pushed
the
config_support_diffusers
branch
from
1cf4b30 to
0ee0b9f
Compare
quic-amitraj
force-pushed
the
config_support_diffusers
branch
from
0ee0b9f to
1e0fbfd
Compare
quic-amitraj
force-pushed
the
config_support_diffusers
branch
2 times, most recently
from
bb01d84 to
00f5286
Compare
quic-amitraj
added
the
Diffusers
quic-amitraj
force-pushed
the
config_support_diffusers
branch
from
00f5286 to
0a26f1b
Compare
quic-amitraj
force-pushed
the
config_support_diffusers
branch
from
ac6382a to
19e0ccd
Compare
ochougul
reviewed
Nov 20, 2025
| . preflight_qeff/bin/activate && | ||
| pip install --upgrade pip setuptools && | ||
| pip install .[test] && | ||
| pip install .[diffusers] && |
Contributor
There was a problem hiding this comment.
better to make a .[all] where we install all the packages required for jenkins
Contributor
Author
There was a problem hiding this comment.
As we dont have the permission of many packages like librosa we can't put those in pyproject, so are you asking to create another .toml with the .[all]?
|
|
||
| # Initialize the FLUX.1-schnell pipeline from pretrained weights | ||
| # use_onnx_function=True enables ONNX-based optimizations for faster compilation | ||
| pipeline = QEFFFluxPipeline.from_pretrained("black-forest-labs/FLUX.1-schnell", use_onnx_function=False) |
Contributor
There was a problem hiding this comment.
In CausalLM models we are adding use_onnx_subfunctions
Lets use same parameter name.
Also, this is a export time decision and we should take this parameter in the same call where we call export which is either in compile/export/__call__ in this case.
We should move this parameter to be accepcted by above mentioned methods.
In CausalLM models we are accepting this parameter in export/compile
Refer to #621 discussion for more details.
Contributor
Author
There was a problem hiding this comment.
Will resolve this.
ochougul
reviewed
Nov 20, 2025
Signed-off-by: Amit Raj <amitraj@qti.qualcomm.com> Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
Signed-off-by: Amit Raj <amitraj@qti.qualcomm.com> Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
Signed-off-by: Amit Raj <amitraj@qti.qualcomm.com> Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
Signed-off-by: Amit Raj <amitraj@qti.qualcomm.com> Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
Signed-off-by: Amit Raj <amitraj@qti.qualcomm.com> Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
Signed-off-by: Amit Raj <amitraj@qti.qualcomm.com> Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
Signed-off-by: Amit Raj <amitraj@qti.qualcomm.com> Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
Signed-off-by: Amit Raj <amitraj@qti.qualcomm.com> Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
Signed-off-by: Amit Raj <amitraj@qti.qualcomm.com> Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
Signed-off-by: Amit Raj <amitraj@qti.qualcomm.com> Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
Signed-off-by: tv-karthikeya <vtirumal@qti.qualcomm.com> Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
Signed-off-by: Amit Raj <amitraj@qti.qualcomm.com> Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
…and export APIs Signed-off-by: Amit Raj <amitraj@qti.qualcomm.com> Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
Signed-off-by: Amit Raj <amitraj@qti.qualcomm.com> Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
…nd comments addressed Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
quic-amitraj
force-pushed
the
config_support_diffusers
branch
from
19e0ccd to
8d78ac9
Compare
Signed-off-by: Amit Raj <amitraj@qti.qualcommm.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
Support for Diffusers Architecture in Efficient Transformers
Overview
This pull request introduces Diffusers architecture support to the Efficient Transformers framework, enabling seamless integration of diffusion models.
Key Highlights
parallel_compile