This is a first Draft of a usable Dockerfile for AMD ROCm cards.
Based on my testing it currently only works with the raw-png branch, probably due to the newer dependencies (9.0.7 on AMD is also broken with micromamba).
The flash_attn handling is also not that pretty, but I'm not sure how to improve it. Feedback is especially welcome here.
I'll also have to do some performance testing to see whether there's any negative impact, and if newer ROCm versions (6.1.2) or even potentially mismatched versions (6.0 on 6.2 or 6.1 on 6.2) improve things.
There might also STILL be some memory leaks during model load, but using Docker and venv compard to micromamba makes bisecting easier.
This is a first Draft of a usable Dockerfile for AMD ROCm cards.
Based on my testing it currently only works with the
raw-png
branch, probably due to the newer dependencies (9.0.7 on AMD is also broken with micromamba).The flash_attn handling is also not that pretty, but I'm not sure how to improve it. Feedback is especially welcome here.
I'll also have to do some performance testing to see whether there's any negative impact, and if newer ROCm versions (6.1.2) or even potentially mismatched versions (6.0 on 6.2 or 6.1 on 6.2) improve things.
There might also STILL be some memory leaks during model load, but using Docker and venv compard to micromamba makes bisecting easier.