cosmos3: switch quant backend in examples to SDNQ ConvRot config - #2886
Merged
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This pull request updates the quantization configuration for several example configs in the
simpletuner/examplesdirectory, switching from the "int8-quanto" precision to the newer "int8-sdnq" method. It also introduces additional SDNQ-specific parameters to further customize quantization behavior. These changes ensure that all Cosmos3 LyCORIS LoKR image configs are aligned with the latest quantization approach.Quantization method update:
base_model_precisionfrom"int8-quanto"to"int8-sdnq"in all affected config files to adopt the SDNQ quantization method. [1] [2] [3] [4] [5]SDNQ-specific parameter additions:
sdnq_compile_mode,sdnq_group_size,sdnq_hadamard_group_size,sdnq_use_hadamard, andsdnq_use_quantized_matmulto all configs, enabling advanced SDNQ features and customization. [1] [2] [3] [4] [5]