add Leptokurtic Quant（LeptoQuant） algorithm#45
Merged
Conversation
yghstill
reviewed
Aug 19, 2025
yghstill
reviewed
Aug 19, 2025
WOODchen7
changed the title
yghstill
approved these changes
Aug 19, 2025
WOODchen7
added a commit
to WOODchen7/AngelSlim
that referenced
this pull request
Aug 27, 2025
Co-authored-by: woodchen7 <woodchenwu@tencent.com>
dawnranger
pushed a commit
to dawnranger/AngelSlim
that referenced
this pull request
Mar 11, 2026
Co-authored-by: woodchen7 <woodchenwu@tencent.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
To address the aforementioned FP8 quantization issues, we introduced Leptokurtic Quant（LeptoQuant） search, a search strategy that concentrates the FP8 weight mapping range into a high-precision region by isolating outliers. Quantizing activations is generally more difficult than quantizing weights, so we prioritize optimizing FP8 activations. LeptoQuant uses the original FP8 outlier values as the upper limit of FP8 precision expression, calculating a new scale that compresses the value distribution into a high-precision distribution range, resulting in better precision expression of quantized activation values.