[MXFP4] Hard code dynamic_mxfp4_quant from aiter.ops.triton.quant#120
Open
Knarf04 wants to merge 1 commit intogpu-mode:mainfrom
Open
[MXFP4] Hard code dynamic_mxfp4_quant from aiter.ops.triton.quant#120Knarf04 wants to merge 1 commit intogpu-mode:mainfrom
Knarf04 wants to merge 1 commit intogpu-mode:mainfrom
Conversation
Contributor
|
LGTM @msaroufim |
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The
dynamic_mxfp4_quantkernel infp4_utils.pyuses incorrect round-ties-up rounding (see ROCm/aiter#974, fixed for quant.py but not yet for fp4_utils.py, tracked in ROCm/aiter#2249).This PR switches the reference kernel's quantization to explicitly use the patched
dynamic_mxfp4_quantfromaiter.ops.triton.quant, with scales shuffled separately viae8m0_shuffle.CC: @msaroufim @danielhua23