Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

Begun to fill the empty CUDA/ROCm doc

Browse Source 
🤡
This commit is contained in:
mauwii 2023-02-08 00:05:24 +01:00
parent 13d12a0ceb
commit 9157da8237
No known key found for this signature in database
GPG Key ID: D923DB04ADB3F5AB
1 changed files with 34 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
docs/installation/030_INSTALL_CUDA_AND_ROCM.md
View File

@ -0,0 +1,34 @@
---
title: NVIDIA Cuda / AMD ROCm
---
<figure markdown>
# :simple-nvidia: CUDA | :simple-amd: ROCm
</figure>
## :simple-nvidia: CUDA
### Container Runtime
Fancy Site: https://developer.nvidia.com/nvidia-container-runtime
GitHub Source: https://github.com/NVIDIA/nvidia-container-runtime/
(where the Fancy Site also links ot xD)
Maybe the most simple way to get InvokeAI running with NVIDIA CUDA will be the official
NVIDIA Container Runtime (not confirmed, but got told by a friend) that the Runtime even
works when you do not have the actual Drivers installed, since it is mounting the GPU
into the Container
## :simple-amd: ROCm
### ROCm-docker
GitHub Source: https://github.com/RadeonOpenCompute/ROCm-docker/blob/master/quick-start.md
Yeah - I am sorry, but since I am not into PC-Masterrace, I had no better Idea than
looking up if there is a container runtime for ROCm as well xD
So please forgive me, but at least the page isn't empty anymore 🙈