feat(performance): migrate sentiment inference to ONNX runtime via Optimum#19
Open
kushagarwal2910-lang wants to merge 1 commit intoruxailab:mainfrom
Open
feat(performance): migrate sentiment inference to ONNX runtime via Optimum#19kushagarwal2910-lang wants to merge 1 commit intoruxailab:mainfrom
kushagarwal2910-lang wants to merge 1 commit intoruxailab:mainfrom
Conversation
Author
|
Hey @marcgc21 and @BasmaElhoseny01 please review this PR and if possible give me you're valuable feedback. |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Resolves #18
Context
To meet the scalability goals for upcoming developments, the API needs to process audio chunks faster without ballooning cloud compute costs. Native PyTorch execution on CPU is unoptimized for production throughput.
Changes Made
optimum[onnxruntime]torequirements.txt.AutoModelForSequenceClassificationwithORTModelForSequenceClassificationinbertweet_model.py.export=Trueflag dynamically builds the ONNX graph on initialization, ensuring zero friction for other developers (no manual.ptto.onnxconversions needed).Impact
pipeline()execution for timestamped audio chunks.I ran the standard tests locally and everything passes smoothly with expected confidence intervals. Let me know if you'd like me to benchmark this against the old PyTorch implementation for the official documentation!