import OVQuantizer only if it is required in VLM #1048
Merged
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
|
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. |
AlexKoff88
approved these changes
Dec 4, 2024
|
@echarlaix, @IlyasMoutawwakil, this is a hotfix for Windows OS users |
|
@echarlaix, @IlyasMoutawwakil, this is a hotfix. |
nikita-savelyevv
approved these changes
Dec 4, 2024
IlyasMoutawwakil
approved these changes
Dec 4, 2024
eaidova
force-pushed
the
ea/lazy_quantizedr_import
branch
from
7d5d9d6 to
97e9141
Compare
eaidova
force-pushed
the
ea/lazy_quantizedr_import
branch
from
b95d78e to
6f6b245
Compare
echarlaix
approved these changes
Dec 4, 2024
github-merge-queue bot
pushed a commit
to openvinotoolkit/openvino.genai
that referenced
this pull request
Dec 5, 2024
together with huggingface/optimum-intel#1048 and huggingface/optimum#2114 allow me run wwb with already exported models on windows platform
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Outdated suggestions cannot be applied.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.
What does this PR do?
in some cases, import OVQuantizer may lead to issues with onnx (import check_dummy_inputs trigger whole initialization of onnx part in optimum), for avoiding this issue in analogy with OVModelForCausalLM I suggest to import it conditionally only in place where it is required as short-term solution. As long-term, we need to extract common part of helper functions from optimum.exporters.onnx to general optimum.exporters.utils (imports will be switched after merge huggingface/optimum#2114 in separated PR)
Before submitting