Allow onnxruntime quantization preprocessor for dynamic quantization#166
Closed
fxmarty wants to merge 1 commit intohuggingface:mainfrom
fxmarty:quantization-preprocessor-dynamic
Closed
Allow onnxruntime quantization preprocessor for dynamic quantization#166fxmarty wants to merge 1 commit intohuggingface:mainfrom fxmarty:quantization-preprocessor-dynamic
fxmarty wants to merge 1 commit intohuggingface:mainfrom
fxmarty:quantization-preprocessor-dynamic
Conversation
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. |
This was referenced May 17, 2022
This pull request was closed.
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
Currently, for the onnxruntime backend, the
QuantizationPreprocessoris usable only for static quantization to exclude nodes to quantize, because the onnx model needs to be already saved when initializingQuantizationPreprocessor, which was handled bypartial_fitmethod used during calibration.With this PR, it is possible to use
QuantizationPreprocessorfor dynamic quantization (if it happens to be relevant at some point -- at least I would like to test it), while making no change to the current workflow.Before submitting
QuantizationPreprocessoris largely (publicly) untested and documented, in a future PR we could improve that.