Skip to content

optimize fp8 inference with AngelSlim#132

Open
GGgary666 wants to merge 2 commits intoTencent-Hunyuan:mainfrom
GGgary666:angelslim_fp8_support_1028
Open

optimize fp8 inference with AngelSlim#132
GGgary666 wants to merge 2 commits intoTencent-Hunyuan:mainfrom
GGgary666:angelslim_fp8_support_1028

Conversation

@GGgary666
Copy link
Copy Markdown

optimize fp8 inference with (AngelSlim)[https://github.com/Tencent/AngelSlim]

Comment thread README.md
model_name = "hunyuanimage-v2.1"
pipe = HunyuanImagePipeline.from_pretrained(model_name=model_name, use_fp8=True)
# Supported fp8_mode: weight_only, w8a8
pipe = HunyuanImagePipeline.from_pretrained(model_name=model_name, fp8_mode="w8a8")
Copy link
Copy Markdown

Choose a reason for hiding this comment

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

这里增加一行weight_only的调用代码,可以注释掉

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