Closed JingyaHuang closed 3 days ago
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.
what happen? I hope it will be merge it soon, aslo sdxl control model too :)
If you push your pull-request back, consider cherry-picking this commit from my branch to fix the TGI docker build.
@dacorvo for the tracing, the compiler only accepts tensors, but not a list or a tuple of tensors which could be the case in transformers. So we flatten (actually we create directly non-nested dummy) inputs during the tracing, and during the inference runtime, we need to flatten inputs generated by the preprocessor (or the output of another model in the pipe like the case of stable diffusion) before feeding it into the compiled model.
What does this PR do?
Fixes #575
[x] Add ControlNet export support
Regular SD
Tiny test
[x] Add ControlNet pipeline for stable diffusion
Compilation
Next Steps
Before submitting