AITemplate
Olive
AITemplate | Olive | |
---|---|---|
37 | 13 | |
4,460 | 1,239 | |
0.8% | 4.7% | |
8.7 | 9.8 | |
4 days ago | 3 days ago | |
Python | Python | |
Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
AITemplate
-
Show HN: Shortbread, a web app that helps you create AI comics in minutes
VoltaML is a relatively vanilla diffusers-based backend, so its not a hairy monster to hack like you may have seen with SAI-based UIs.
The AITTemplate code is a lightly modified version of Facebook's example, code, to get rid of small issues like VRAM spikes: https://github.com/facebookincubator/AITemplate/tree/main/ex...
InvokeAI is also diffusers based, but they seem to mess with the pipeline a bit more.
And anyway, all that may be a better reference for interesting features rather than a backend to try and adopt.
-
List of all the ways to improve performance for stable diffusion.
let me know if you discover any more ways to improve SD. I am currently looking into facebooks AITemplate : https://github.com/facebookincubator/AITemplate
- [R] AITemplate Python to AMD compiler {META}
-
Nearly 2x speedup for SD rendering using AITemplate
Link to AITemplate itself: https://github.com/facebookincubator/AITemplate
- Render a neural network into CUDA/HIP code
- Render neural network into CUDA/HIP code
- AITemplate: a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.
- A1111 vs Olive vs AITemplate.
Olive
- FLaNK Stack Weekly for 12 June 2023
-
Unpaint: a compact, fully C++ implementation of Stable Diffusion with no dependency on python
I use Microsoft Olive to optimize my networks. It works rather well as I did make my inference speed like 2-3 times faster, the models smaller and VRAM usage was reduced as well, though this needs the latest nvidia drivers to happen.
-
A1111 vs Olive vs AITemplate.
First update drivers, then follow the instruction here: Olive/README.md at main · microsoft/Olive · GitHub I try SD1.5 and DreamShaper model, both hit 30it/s
- I have created Olive model. But what is the next step? Who knows?
-
AMD support for Microsoft® DirectML optimization of Stable Diffusion
Microsoft has provided a path in DirectML for vendors like AMD to enable optimizations called ‘metacommands’. In the case of Stable Diffusion with the Olive pipeline, AMD is building driver support for a metacommand implementation intended to improve performance and reduce the time it takes to generate output from the model. This feature will be validated on AMD RDNA™ 3 devices including AMD Radeon™ RX 7900 Series graphics cards and AMD Ryzen™ 7040 Series Mobile processors with Radeon™ graphics.
-
Nvidia:"2x performance improvement for Stable Diffusion coming in tomorrow's Game Ready Driver"
Olive is an easy-to-use hardware-aware model optimization tool that composes industry-leading techniques across model compression, optimization, and compilation. Given a model and targeted hardware, Olive composes the best suitable optimization techniques to output the most efficient model(s) for inferencing on cloud or edge, while taking a set of constraints such as accuracy and latency into consideration.
-
NVIDIA and Microsoft Drive Innovation for Windows PCs in New Era of Generative AI
Repository: https://github.com/microsoft/Olive
- Nvidia: "2x performance improvement for Stable Diffusion coming in tomorrow's Game Ready Driver"
What are some alternatives?
stable-diffusion-webui - Stable Diffusion web UI
chatdocs - Chat with your documents offline using AI.
nebuly - The user analytics platform for LLMs
StableDiffusionUI - Stable Diffusion UI: Diffusers (CUDA/ONNX)
xformers - Hackable and optimized Transformers building blocks, supporting a composable construction.
documenso - The Open Source DocuSign Alternative.
voltaML - ⚡VoltaML is a lightweight library to convert and run your ML/DL deep learning models in high performance inference runtimes like TensorRT, TorchScript, ONNX and TVM.
SDAtom-WebUi-us - Queue system for AUTOMATIC1111's webui
stable-diffusion-tensorflow - Stable Diffusion in TensorFlow / Keras
unpaint - A simple Windows / Xbox app for generating AI images with Stable Diffusion.
rocm-gfx803
stable-diffusion-webui-directml - Stable Diffusion web UI