Comments (19)
if you have the K80 and want to add it to the supported list, run :
!pip install git+https://github.com/facebookresearch/xformers@51dd119#egg=xformers
after around 40min, and the installation is done, navigate to /usr/local/lib/python3.7/dist-packages/xformers
save the two files : "_C_flashattention.so" and "_C.so", upload them to any host and send me the link and I will integrate them in the Colab for K80 users.
the files might not show in the colab explorer, so you will have to rename them
!cp /usr/local/lib/python3.7/dist-packages/xformers/_C.so /usr/local/lib/python3.7/dist-packages/xformers/C.py
!cp /usr/local/lib/python3.7/dist-packages/xformers/_C_flashattention.so /usr/local/lib/python3.7/dist-packages/xformers/C_flashattention.py
from fast-stable-diffusion.
The C/C++/Cuda code responsible for the xformers-specific operations (memory efficient attention included) for the underlying machine (python version, cuda, ..)
from fast-stable-diffusion.
Sorry, I completely forgot about it, I'll add it as soon as I'm done with the new Dreambooth method
from fast-stable-diffusion.
In a few hours it will be added to the colabs
from fast-stable-diffusion.
did you make a clean run with an update colab from the repo ?
Not sure, will try it now and report back.
... or perhaps not now, but when I get A100 again 🤷♂️
from fast-stable-diffusion.
For the K80 ? 287 KB looks a bit small, it should be at least 19mb, maybe it didn't compile well. try compiling it with google colab if you get the K80
I'll let you know if I can get the files from a K80 colab. Right now all my accounts have a usage limit of no GPU, or are getting T4s, though, so it might be a while.
from fast-stable-diffusion.
Hi. I am using collab pro and very often I have a100 gpu assigned. How can you add to the gpu ?
from fast-stable-diffusion.
Perhaps this is the right issue. Running on A100 (colab), getting spammed in the output:
FATAL: this function is for sm80, but was built for sm600
from fast-stable-diffusion.
did you make a clean run with an update colab from the repo ?
from fast-stable-diffusion.
@TheLastBen , actually, that doesn't seem to be A100-specific issue.
On V100 I see:
FATAL: this function is for sm70, but was built for sm600
Running freshly opened:
https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb
Is it a regression?
Will try to reproduce on clean AUTOMATIC1111
UI without attention patch.
UPD: confirmed, clean AUTOMATIC1111
works on V100, the issue is introduced by the patch.
from fast-stable-diffusion.
try to reproduce the error with a T4 (free colab)
from fast-stable-diffusion.
also try other colabs if the same issue happens
from fast-stable-diffusion.
save the two files : "_C_flashattention.so" and "_C.so", upload them to any host and send me the link and I will integrate them in the Colab for K80 users
I did this, but am using conda, so the directories don't match up. I found /home/ben/.conda/envs/my-env/lib/python3.10/site-packages/xformers
, but there's no _C_flashattention.so
in it, or anywhere on the system.
I did find _C.so
, though; it's here
from fast-stable-diffusion.
For the K80 ?
287 KB looks a bit small, it should be at least 19mb, maybe it didn't compile well. try compiling it with google colab if you get the K80
from fast-stable-diffusion.
@TheLastBen I was able to install xformers with a bigger _C.so
file (13.1 MB) by un-init
-ing conda, and got this. I still don't have a _C_flashattention.so
anywhere on my system, though.
from fast-stable-diffusion.
GPUs unsupported by flash attention don't produce a _C_flashattention.so
after compiling, but they still benefit from a speed increase
from fast-stable-diffusion.
GPUs unsupported by flash attention don't produce a
_C_flashattention.so
after compiling, but they still benefit from a speed increase
Ok, thanks. Quick question: what is _C_flashattention.so
for/what does it do?
from fast-stable-diffusion.
@TheLastBen Would you be able to make the whl using that file and add it? I'd make the whl and do a new PR, but it's not working for me.
from fast-stable-diffusion.
@TheLastBen Would you be able to make the whl using that file and add it? I'd make the whl and do a new PR, but it's not working for me.
Just added, if you get the K80 try it in A1111 Colab and let me know if the wheel works.
from fast-stable-diffusion.
Related Issues (20)
- Error in the first cell.
- Error when starting "Start Stable-Diffusion" while "fast_stable_diffusion" is running etc... HOT 2
- Chechpoint/model consistency
- Google Colab Pro | No share link in Start Stable-Diffusion Cell HOT 10
- automatic1111 won't start up HOT 11
- Google Colab | No share link without Cloudflare Tunnel HOT 5
- Unable to launch ComfyUI in Paperspace, tensorboard link "Service Unavailable" HOT 5
- Google collab is not working for more than 3 months already - What's the point then?
- Could not create share link. Missing file: /usr/local/lib/python3.10/dist-packages/gradio/frpc_linux_amd64_v0.2.
- gradio link not showing up HOT 1
- faststablediffusion
- FileNotFoundError [Paperspace] HOT 16
- GOOGLE COLLAB works well for 2 days, then breaks. Why? HOT 4
- Something went wrong
- HOW TO USE MODEL FROM SDXL in TheLastBen Stable Diffusion? HOT 3
- Error merging checkpoints: Error while serializing: IoError(Os { code: 2, kind: NotFound, message: "No such file or directory" })
- Problem using SDXL model on colab HOT 1
- RunPod / RNPD-A1111 not able to start
- Official Runpod model does not work: runpod/stable-diffusion:fast-stable-diffusion-2.4.0
- (Fix Guide) Paperspace Python3.9 is missing HOT 12
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from fast-stable-diffusion.