Skip to content

refactor dit fp8 quant, support fp8 weight export#99

Merged
yghstill merged 5 commits into
Tencent:mainfrom
GGgary666:diffusion_quant_refactor_1022
Oct 25, 2025
Merged

refactor dit fp8 quant, support fp8 weight export#99
yghstill merged 5 commits into
Tencent:mainfrom
GGgary666:diffusion_quant_refactor_1022

Conversation

@GGgary666
Copy link
Copy Markdown
Contributor

update dit fp8 quant api with convert_linear and export_quantized_weight

) from e


def load_fp8_scales(
Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

新建utils文件夹,utils.py也迁移进去,load和save相关可以和通用util分离,新建一个py文件存放,eg: quant_io.py


## Quick Start: FP8 Quantization for Diffusion Models

### Method 1: Quantize with Pre-computed Scales
Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

量化文档在docs/source/features/diffusion也建一个

@yghstill yghstill merged commit 8249909 into Tencent:main Oct 25, 2025
5 checks passed
dawnranger pushed a commit to dawnranger/AngelSlim that referenced this pull request Mar 11, 2026
Co-authored-by: garygugong <garygugong@tencent.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants