stable-diffusion VS tvm

No, sorry, but there's a whole bunch of one-click things now, I think?

I'm running it on Windows 10 using (a modified version of) https://github.com/bfirsh/stable-diffusion.git and Anaconda to create the environment from their `environment.yaml` (all of which was done using the normal `cmd` shell). Then to use it, I activate that env from `cmd` and switch into cygwin `bash` to run the `txt2img.py` script (because it's easier to script, etc.)

I am using the bfirsh version. And yes, I run "pyhthon scripts/txt2imp.py" to generate an image.

Specifically regarding the first option above, I see that the procedure clones the repository from: https://github.com/bfirsh/stable-diffusion.git

Just done a run on my 3080 under Windows using https://github.com/bfirsh/stable-diffusion.git and it's about 8 iterations/sec when nothing else is using CPU or GPU.

I've cloned this repository on my M1 Mac: https://github.com/bfirsh/stable-diffusion/tree/apple-silicon-mps-support

Boom - nice. Here's a fork with that: https://github.com/bfirsh/stable-diffusion/tree/lstein

Requirements are "requirements-mac.txt" which'll need subbing in the guide.

We're testing this out with a few people in Discord before shipping to the blog post.

Yes, this is coming! Myself and others at OctoML and in the TVM community are actively working on multi-gpu support in the compiler and runtime. Here are some of the merged and active PRs on the multi-GPU (multi-device) roadmap:

Support in TVM’s graph IR (Relax) - https://github.com/apache/tvm/pull/15447

Would it make sense to have a backend support for OpenXLA, Apache TVM, Jittor or other similar to get free GPU, TPU and other accelerators for free ?

I have tried the iPhone app. It's fast. They're using Apache TVM which should allow better use of native accelerators on different devices. Like using metal on Apple and Vulcan or CUDA or whatever instead of just running the thing on the CPU like llama.cpp.

I was going to answer the same, I find the approach of machine learning compilers that directly compile models to host and device code better than having to bring a huge runtime. There are exciting projects in this area like TVM Unity, IREE [2], or torch.export [3]

[1] https://github.com/apache/tvm/tree/unity

[2] https://pytorch.org/get-started/pytorch-2.0/#inference-and-e...

[3] https://pytorch.org/get-started/pytorch-2.0/#inference-and-e...

Apache TVM home page: https://tvm.apache.org/

It's pretty clear its referring to the output of Apache TVM and Meta's Glow

As mentioned in sibling comments, Torch is indeed the glue in this implementation. Other glues are TVM[0] and ONNX[1]

These just cover the neural net though, and there is lots of surrounding code and pre-/post-processing that isn't covered by these systems.

For models on Replicate, we use Docker, packaged with Cog for this stuff.[2] Unfortunately Docker doesn't run natively on Mac, so if we want to use the Mac's GPU, we can't use Docker.

I wish there was a good container system for Mac. Even better if it were something that spanned both Mac and Linux. (Not as far-fetched as it seems... I used to work at Docker and spent a bit of time looking into this...)

[0] https://tvm.apache.org/

Or use TVM, the idea is to compile your model into code that you can load at runtime. Similar to onnxruntime, it only does DNN inference; so you need domain-specific code.

Open-source projects leveraged by nebullvm include OpenVINO, TensorRT, Intel Neural Compressor, SparseML and DeepSparse, Apache TVM, ONNX Runtime, TFlite and XLA. A huge thank you to the open-source community for developing and maintaining these amazing projects.