Workaround for SD alt compilation/demo for T4 SM75

[apivovarov]

Description

Currently compile_alt.py generates bad images on T4 GPU (SM75). Related issue - https://github.com/facebookincubator/AITemplate/issues/781 Notebook to reproduce the issue with bad images on T4 GPU - AIT_alt_bad_image.ipynb

I found that the issue with bad images can be fixed if we use the following workaround:

1. compile_clip_alt.py - batch higher dim should be 8+
2. compile_unet_alt.py - Both lower and upper batch dims should be doubled

I understand that the workaround above uses magic numbers. But it works...

Testing

Tested on T4 and A100 GPUs .

Compiled with different batch ranges (1-8, 2-4, 1-9) and run demo_alt with different batch sizes (1,2,4,8,9) - all images look ok.