Git Product home page Git Product logo

Comments (5)

bolshoytoster avatar bolshoytoster commented on August 21, 2024 1

The problem here, is that torch couldn't identify your gpu's CC (compute capability). You have to tell it by defining an environment variable TORCH_CUDA_ARCH_LIST to your gpu's CC +'+PTX', e.g. in bash:

TORCH_CUDA_ARCH_LIST=5.0+PTX

Then run pip install . again.

If you don't know your gpu's CC, if you have an NVIDIA gpu you can run nvidia-smi to get the model if you don't know it already, then look it up in this table:

If you don't have an NVIDIA gpu you'll have to look up the CC by it's model on the internet.

Unrelated, it's generally considered bad practise to run pip as root.

from svox2.

bolshoytoster avatar bolshoytoster commented on August 21, 2024 1

@dadaphl sorry, I can’t seem to find the exact article, but I think got it from something on mylifeismymessage.net.

I did find a wikipedia article that might contain your gpu. Look for ‘Compute ability’ or ‘CUDA Compute ability’ in the tables (it looks like it only gives it for the GeForce 8xxx and tesla series’)

from svox2.

weiforce avatar weiforce commented on August 21, 2024

The problem here, is that torch couldn't identify your gpu's CC (compute capability). You have to tell it by defining an environment variable TORCH_CUDA_ARCH_LIST to your gpu's CC +'+PTX', e.g. in bash:

TORCH_CUDA_ARCH_LIST=5.0+PTX

Then run pip install . again.

If you don't know your gpu's CC, if you have an NVIDIA gpu you can run nvidia-smi to get the model if you don't know it already, then look it up in this table:

If you don't have an NVIDIA gpu you'll have to look up the CC by it's model on the internet.

Unrelated, it's generally considered bad practise to run pip as root.

It worked! Thanks.

from svox2.

dadaphl avatar dadaphl commented on August 21, 2024

If you don't know your gpu's CC, if you have an NVIDIA gpu you can run nvidia-smi to get the model if you don't know it already, then look it up in this table:

@bolshoytoster could you please post a link to this table? My (fairly new) nvidia gpu is not listed in the screenshot. I assume it might have been updated but i can not find this table on the nvidia site. thanks.

from svox2.

soumendra avatar soumendra commented on August 21, 2024

I had to use export TORCH_CUDA_ARCH_LIST="6.1 7.5 8.6" for it to work.

from svox2.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo 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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.