DeepSpeed-MII
rocm-gfx803
Our great sponsors
| DeepSpeed-MII | rocm-gfx803 | |
|---|---|---|
| 6 | 7 | |
| 1,629 | 167 | |
| 7.0% | - | |
| 8.7 | 1.1 | |
| 6 days ago | about 1 year ago | |
| Python | ||
| 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.
DeepSpeed-MII
- Stable Diffusion plus DeepSpeed
-
[D] When chatGPT stops being free: Run SOTA LLM in cloud
Microsoft/DeepSpeed-MII for an up 40x reduction on inference cost on Azure, this thing also supports int8 and fp16 bloom out of the box, but it fails on Azure due to instance size.
- Image Creation Time for each GPU.
-
Anyone tried DeepSpeed-MII with stablediffusion?
Haven't tried it yet but they have some example code here: https://github.com/microsoft/DeepSpeed-MII/blob/main/examples/local/txt2img-example.py
- [P] Pure C/C++ port of OpenAI's Whisper
rocm-gfx803
- ROCm gfx803 archlinux
-
My brother is giving away a PC he built with 8 AMD Radeon RX Vega x64 GPUs (8GB ram). I've only ever done ML on Nvidia cards. Is there anything I can do with these?
That specific card has current support for rocm and that is supported by at least tensorflow and torch, plus many other less known/used libraries like cupy, although you are correct in the fact that support sucks in the long run, I have a GPU that is known to be useful and that has continued COMMUNITY support because AMD cut the support with rocm 4.0, thanks to Xuhuisheng for the patch to make the rx580 work with current rocm despite AMD lack of support, what open source can accomplish https://github.com/xuhuisheng/rocm-gfx803
-
Automatic111 - Torch is not able to use GPU. Help!
You'll also need to compile pytorch and torchvision for gfx803, although I recommend you install the whl files from here inside your venv because it's a massive pain to compile them on non-Ubuntu (I tried)
-
Image Creation Time for each GPU.
I followed the guide from here: https://github.com/xuhuisheng/rocm-gfx803
-
I *think* it's impossible to run SD on an RX 570 (and probably below?)
There is an unofficial build of ROCm 5.2.0 + pytorch + torchvision with GFX8 support added back in. I have no idea if it works. Perhaps someone who knows Docker/Conda could get SD working with those files.
- Run Stable Diffusion on Intel CPUs
What are some alternatives?
whisper.cpp - Port of OpenAI's Whisper model in C/C++
stable-diffusion-webui-docker - Easy Docker setup for Stable Diffusion with user-friendly UI
petals - 🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
AITemplate - AITemplate is 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.
xformers - Hackable and optimized Transformers building blocks, supporting a composable construction.
stable-diffusion-cpu
openvino - OpenVINOâ„¢ is an open-source toolkit for optimizing and deploying AI inference
whisper-rs - Rust bindings to https://github.com/ggerganov/whisper.cpp
stable-diffusion - Go to lstein/stable-diffusion for all the best stuff and a stable release. This repository is my testing ground and it's very likely that I've done something that will break it.
XNNPACK - High-efficiency floating-point neural network inference operators for mobile, server, and Web
stable_diffusion.openvino