Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add bfloat16 support #8459

Open
byphilipp opened this issue Jan 7, 2024 · 0 comments
Open

Add bfloat16 support #8459

byphilipp opened this issue Jan 7, 2024 · 0 comments
Labels
feature request Suggest an idea on this project

Comments

@byphilipp
Copy link

Concisely describe the proposed feature
I'm trying to use Taichi to speed up traceformers-like neural network. I encounter float16 type overflow and have to use float32 where it is not necessary.
The bfloat16 type can help with this, but it is unsupported in taichi now
@byphilipp byphilipp added the feature request Suggest an idea on this project label Jan 7, 2024
@github-project-automation github-project-automation bot moved this to Untriaged in Taichi Lang Jan 7, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
feature request Suggest an idea on this project
Projects
Taichi Lang
Status: Untriaged
Milestone
No milestone
Development

No branches or pull requests
1 participant
@byphilipp