Very SLOW and UNSTABLE on directml

I am using the repository and a111's webui on the same machine with directml.
At first,it always use NORMAL_VRAM though I have passed --no_vram.
So I changed the code in comfy/model_management.py,made it work.
However,with the same params(NO_VRAM in comfy,LOW_VRAM in webui) and the same prompt,sampler,model,comfy is even slower than webui(60s/it on comfy,15s/it on webui),even the virtual environment is the same one.
_My computer is not very powerful._😄
When I used pytorch_crossattention,the program exited itself after 1 step.
bf16 on my device will cause directml errors.
And I can't use fp8 because pytorch has no attribute float8_**.(I tried that because I have only 2GB VRAM😂)
But on a 2GB Invida card(GTX750Ti) with xformers,it worked very well as if it was RTX4090👍.
After some times,I cannot generate anything on my AMD card.
I don't know what happened and I'm not very good in Python.
Is there anything I can do?