flux2: switch quant backend to use SDNQ int8 ConvRot instead of int8-torchao and quanto - #2887
Merged
Merged
Conversation
…torchao and quanto
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 two example LoRA training setups to use the SDNQ quantization method and introduces several new SDNQ-specific parameters to the configuration files. These changes are aimed at enabling and fine-tuning SDNQ quantization for improved performance and flexibility.
Quantization method update:
base_model_precisionfrom"int8-quanto"to"int8-sdnq"in bothflux2.peft-lora/config.jsonandflux2.peft-lora+TREAD/config.json, switching the quantization backend to SDNQ. [1] [2]Addition of SDNQ-specific configuration parameters:
"sdnq_compile_mode"set to"compile"to enable compilation mode."sdnq_group_size"set to-1(likely indicating auto or default grouping)."sdnq_hadamard_group_size"set to128to configure Hadamard group size."sdnq_use_hadamard"set totrueto enable Hadamard-based quantization."sdnq_use_quantized_matmul"set totrueto use quantized matrix multiplication. [1] [2]