voltaML
AITemplate
voltaML | AITemplate | |
---|---|---|
5 | 37 | |
1,184 | 4,455 | |
0.0% | 0.7% | |
10.0 | 8.7 | |
over 1 year ago | 2 days ago | |
Python | Python | |
Apache License 2.0 | Apache License 2.0 |
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.
voltaML
- Very first testing version of voltaML is out (giant speed increase)
- VoltaML – convert DL models in high performance inference runtimes
-
[R] Upto 2.5X speed up of Stable-diffusion/Dreambooth using one line of code with voltaML.
Please follow here-> https://github.com/VoltaML/voltaML
-
Upto 2.5X speed up of Stable-diffusion/Dreambooth using one line of code with voltaML.
Follow us here to get updates on the SD acceleration -> https://github.com/VoltaML/voltaML
- [R] Open source inference acceleration library - voltaML
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.
What are some alternatives?
x-stable-diffusion - Real-time inference for Stable Diffusion - 0.88s latency. Covers AITemplate, nvFuser, TensorRT, FlashAttention. Join our Discord communty: https://discord.com/invite/TgHXuSJEk6
stable-diffusion-webui - Stable Diffusion web UI
sd_dreambooth_extension
nebuly - The user analytics platform for LLMs
jukebox - Code for the paper "Jukebox: A Generative Model for Music"
xformers - Hackable and optimized Transformers building blocks, supporting a composable construction.
stable-diffusion-tensorflow - Stable Diffusion in TensorFlow / Keras
rocm-gfx803
DeepSpeed-MII - MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
HIP-CPU - An implementation of HIP that works on CPUs, across OSes.