Add quantization scripts #1
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
…ter integrated with typer
…e isn't reduced???
adrianlyjak
added a commit
that referenced
this pull request
Feb 21, 2025
* start quant calibration, and remove loguru for rich, since that's better integrated with typer * giving up on ORT quantization * prep for rewrite float_to_float16 * add custom float16 conversion implementation * trying to fix bugs * gonna take my own stab at it * fuckit * wip fuckit * fuckit complete * hmm, this exports now. Sorta wrong, should have value infos.Also, size isn't reduced??? * messy messy * now it "converts" to fp16, but no longer producing sound * oh boy, its all useless? neural_encoder _does_ do mixed precision quantization * trying to figure out intel neural compressor * better gpu support for INC * better gpu support for INC * add onnxruntime-gpu * start configuration for experimenting with op selection and quant level * grr inc stupid * hmm, is the reference quant dynamic? * Wrap it up
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Outdated suggestions cannot be applied.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.
No description provided.