CANN: Resolve soft_max precision issue #15730
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
Previously, the slope tensor was set to fp16 to improve efficiency. While this worked correctly in FA, it caused precision issues in soft_max. This change applies different data types for different operators to balance both accuracy and performance.
github-actions
bot
added
ggml
walidbr
pushed a commit
to walidbr/llama.cpp
that referenced
this pull request
Sep 7, 2025
Previously, the slope tensor was set to fp16 to improve efficiency. While this worked correctly in FA, it caused precision issues in soft_max. This change applies different data types for different operators to balance both accuracy and performance.
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Outdated suggestions cannot be applied.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.
Previously, the slope tensor was set to fp16 to improve efficiency. While this worked correctly in FA, it caused precision issues in soft_max. This change applies different data types for different operators to balance both accuracy and performance.
Make sure to read the contributing guidelines before submitting a PR