Add process_prequantized_params to Qwix PTQ provider.#231
Merged
copybara-service[bot] merged 1 commit intomainfrom Mar 27, 2026
Merged
Add process_prequantized_params to Qwix PTQ provider.#231copybara-service[bot] merged 1 commit intomainfrom
process_prequantized_params to Qwix PTQ provider.#231copybara-service[bot] merged 1 commit intomainfrom
Conversation
b0a5c13 to
2d9357f
Compare
This change introduces a new function, process_prequantized_params, which allows loading pre-quantized parameters (e.g., from Orbax checkpoints) into a Qwix PTQ model. The function takes a tree of pre-quantized parameters and an abstract PTQ model to reconstruct the necessary `WithAux` structures, handling sharding and validating the payload format. New tests are added to cover various scenarios, including sharded Einsum layers and asymmetric quantization. PiperOrigin-RevId: 890230892
2d9357f to
c4f31ee
Compare
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add
process_prequantized_paramsto Qwix PTQ provider.This change introduces a new function, process_prequantized_params, which allows loading pre-quantized parameters (e.g., from Orbax checkpoints) into a Qwix PTQ model. The function takes a tree of pre-quantized parameters and an abstract PTQ model to reconstruct the necessary
WithAuxstructures, handling sharding and validating the payload format.New tests are added to cover various scenarios, including sharded Einsum layers and asymmetric quantization.