Update Case 1 to recognize both quantized dict and WithAux as prequantized template.#266
Open
copybara-service[bot] wants to merge 1 commit intomainfrom
Open
Update Case 1 to recognize both quantized dict and WithAux as prequantized template.#266copybara-service[bot] wants to merge 1 commit intomainfrom
copybara-service[bot] wants to merge 1 commit intomainfrom
Conversation
…tized template.
Qwen 3.5 MoE overrides the original fp template (non-intercepted operations are not wrapped in WithAux) for Pallas_call to be a dict like {'array': {'qvalue': ..., 'scale': ...}}. Previously, this falls back to Case 2 "checkpoint is prequantized, template is fp" because it is a non-WithAux quantized format. With this change, this accurately categorizes to Case 1 "checkpoint is prequantized, template is prequantized".
PiperOrigin-RevId: 908764879
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Update Case 1 to recognize both quantized dict and WithAux as prequantized template.
Qwen 3.5 MoE overrides the original fp template (non-intercepted operations are not wrapped in WithAux) for Pallas_call to be a dict like {'array': {'qvalue': ..., 'scale': ...}}. Previously, this falls back to Case 2 "checkpoint is prequantized, template is fp" because it is a non-WithAux quantized format. With this change, this accurately categorizes to Case 1 "checkpoint is prequantized, template is prequantized".