Repository navigation
fix: skip exporting fp8 attention q_max - #2103
Merged
Merged
Conversation
Collaborator
|
/azp run Unit-Test-CUDA-AutoRound |
|
Azure Pipelines will not run the associated pipelines, because the pull request was updated after the run command was issued. Review the pull request again and issue a new run command. |
Collaborator
|
/azp run Unit-Test-CUDA-AutoRound |
|
Azure Pipelines successfully started running 1 pipeline(s). |
Collaborator
|
/azp run Unit-Test-CUDA-AutoRound |
|
Azure Pipelines successfully started running 1 pipeline(s). |
chensuyue
approved these changes
Jul 31, 2026
chensuyue
left a comment
Contributor
There was a problem hiding this comment.
XPU test issue not related to this PR.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
q_maxcalibration tensor during immediate shard writesq_scale,k_scale, andv_scalein exported checkpointsllm_compressorandauto_roundformatsRoot cause
clean_up_hooked_attention()removesq_maxfrom the in-memory model, but immediate saving writes shard files before that cleanup runs. As a result,q_maxleaked into exported safetensors even though it is calibration-only.Validation
nm-testing/tinysmokeqwen3+static_attention_dtype=fp8+format=llm_compressorqmax_count = 0q_scale_count = 6k_scale_count = 6v_scale_count = 6format=auto_roundqmax_count = 0q_scale_count = 6k_scale_count = 6v_scale_count = 6