Enable support for FP4 weight quantization for non-conv layers - #34
Merged
pareshs44 merged 1 commit intoJul 13, 2026
Merged
Conversation
vineet-g
reviewed
Jul 11, 2026
pkmandke
reviewed
Jul 13, 2026
pareshs44
force-pushed
the
enable_fp4_quantization_for_non_conv_layers
branch
from
July 13, 2026 11:57
2cbd426 to
ae88ade
Compare
pkmandke
previously approved these changes
Jul 13, 2026
vineet-g
previously approved these changes
Jul 13, 2026
pareshs44
force-pushed
the
enable_fp4_quantization_for_non_conv_layers
branch
from
July 13, 2026 16:36
ae88ade to
24ff1fb
Compare
pkmandke
approved these changes
Jul 13, 2026
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 PR enables FP4 quantization using coreai-opt, by fixing the following issues:
validate_fp4_exportmethod to enable 4D tensors as well with 32 block size.I tested these changes by using fp4 compression for exporting models, then running the benchmark on GPU. I have also added some unit tests to verify these paths.