Open andreasjansson opened 3 weeks ago
Very excited for this PR. Thanks for doing this! I was looking for an H100 lora inference provider and this seems like it would do the trick. I was curious as well if pricing for fast generations would be any different than per image because the GPU usage time is much less?
Hi, I was curious if this work is continuing on this PR? I believe this should make flux dev lora inference fast enough that you'd gain a customer versus using Fal as they currently are a few seconds faster (but from my benchmarking, this should be faster in the end). Happy to take on any tasks if you would like as well.
Had to fix some bugs in the original lora loading code.
Outputs are here: https://replicate.com/replicate-internal/test-flux-dev-lora
Fusing and unfusing is also slightly lossy so the model slowly degrades over time. We could do something like what peft and add a new node that does the matmul on the fly, instead of fusing. But that would slow down inference. Curious if you have ideas @daanelson