For Z-Image, the performance of the stock version of chromaForge is poorer than sd.cpp's. Mainly because chromaForge isn't able to run the smaller gguf quantized models that sd.cpp is able to run (chromaForge fails with the errors that I was fixing yesterday).
Worked on fixing Z-Image support in ED's fork of chromaForge (a fork of Forge WebUI). Fixed a number of integration issues. It's now crashing on a matrix multiplication error, which looks like an incorrectly transposed matrix (mostly due to reading the weights in the wrong order).
Collecting the worklog over the past few weeks.
The new engine that'll power Easy Diffusion's upcoming v4 release (i.e. sdkit3) has now been integrated into Easy Diffusion. It's available to test by selecting v4 engine in the Settings tab (after enabling Beta). Please press Save and restart Easy Diffusion after selecting this.
Following up to the deep-dive on ML compilers:
This post concludes (for now) my ongoing deep-dive into ML compilers, while researching for sdkit v3. I've linked (at the end) to some of the papers that I read related to graph execution on GPUs.
Good post on using MLIR for compiling ML models to GPUs. It gives a good broad overview of a GPU architecture, and how MLIR fits into that. The overall series looks pretty interesting too!
Wrote a fresh implementation of most of the popular samplers and schedulers used for image generation (Stable Diffusion and Flux) at https://github.com/cmdr2/samplers.cpp. A few other schedulers (like Align Your Steps) have been left out for now, but are pretty easy to implement.
Some notes on machine-learning compilers, gathered while researching tech for Easy Diffusion's next engine (i.e. sdkit v3). For context, see the design constraints of the new engine.
The design constraints for Easy Diffusion's next engine (i.e. sdkit v3) are: