theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-24 18:28:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

support qwen-image-fp8

Browse Source
This commit is contained in:
Artiprocher
2025-08-07 16:20:50 +08:00
parent d20680baae
commit a0eec8c673
7 changed files with 224 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
examples/qwen_image/README_zh.md
View File

@@ -172,7 +172,11 @@ FP8 量化能够大幅度减少显存占用，但不会加速，部分模型在
<summary>推理加速</summary>
Qwen-Image 的推理加速技术正在开发中，敬请期待！
* FP8 量化：根据您的硬件与需求，请选择合适的量化方式
* GPU 不支持 FP8 计算（例如 A100、4090 等）：FP8 量化仅能降低显存占用，无法加速，代码：[./model_inference_lor_vram/Qwen-Image.py](./model_inference_lor_vram/Qwen-Image.py)
* GPU 支持 FP8 运算（例如 H200 等）：请安装 [Flash Attention 3](https://github.com/Dao-AILab/flash-attention)，否则 FP8 加速仅对 Linear 层生效
* 更快的速度，但更大的显存：请使用 [./accelerate/Qwen-Image-FP8.py](./accelerate/Qwen-Image-FP8.py)
* 稍慢的速度，但更小的显存：请使用 [./accelerate/Qwen-Image-FP8-offload.py](./accelerate/Qwen-Image-FP8-offload.py)
</details>