A800 inference speed too slow

[Tttobi4s]

Self Checks

• This template is only for bug reports. For questions, please visit Discussions.
• I have thoroughly reviewed the project documentation (installation, training, inference) but couldn't find information to solve my problem. English 中文 日本語 Portuguese (Brazil)
• I have searched for existing issues, including closed ones. Search issues
• I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
• Please do not modify this template and fill in all required fields.

Cloud or Self Hosted

Cloud, Self Hosted (Source)

Environment Details

A800

Steps to Reproduce

I used the A800 to run run_webui.py in Speech-Fish and found that the token generation speed is very unstable(I have used the --compile parameter). Is this related to the type of Nvidia GPU? I noticed that it performs excellently on the 4090. Here is the log:

✔️ Expected Behavior

No response

❌ Actual Behavior

No response

[PoTaTo-Mika]

No other similar issues about it, please check the GPU and your torch version.