Add quantized PyTorch models in model builder #600
Merged
+841
−62
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
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
yufenglee
reviewed
Jun 12, 2024
yufenglee
reviewed
Jun 12, 2024
yufenglee
approved these changes
Jun 18, 2024
kunal-vaishnavi
added a commit
that referenced
this pull request
Jun 28, 2024
### Description This PR adds an end-to-end example for quantizing a PyTorch model with [AutoAWQ](https://github.com/casper-hansen/AutoAWQ), creating the corresponding optimized and quantized ONNX model, and running the ONNX model with ONNX Runtime GenAI. ### Motivation and Context This PR shows an end-to-end example for [the quantized PyTorch support in the model builder](#600).
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Outdated suggestions cannot be applied.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.
Description
This PR adds support for building the final ONNX models that are optimized and quantized from already-quantized PyTorch models.
Motivation and Context
Quantization methods supported for already-quantized PyTorch models are GPTQ and AWQ. Currently, only INT4 precision is supported.