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

[pallas] Add support for the new algorithm option to dot #23926

Open
sbodenstein opened this issue Sep 25, 2024 · 0 comments
Open

[pallas] Add support for the new algorithm option to dot #23926

sbodenstein opened this issue Sep 25, 2024 · 0 comments
Labels
enhancement New feature or request pallas Issues pertaining to Pallas (GPU or TPU)

Comments

@sbodenstein
Copy link
Contributor

jax.lax.dot_general has a new algorithm option for precisely specifying the precision, which should be supported in Pallas. Also support the simulated precision modes on GPU, such as BF16_BF16_F32_x6 and TF32_TF32_F32_x3 (already supported by triton.language.dot via the input_precision="tf32x3" option).

@chr1sj0nes, @sharadmv, @dfm
@sbodenstein sbodenstein added the enhancement New feature or request label Sep 25, 2024
@superbobry superbobry added the pallas Issues pertaining to Pallas (GPU or TPU) label Sep 26, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement New feature or request pallas Issues pertaining to Pallas (GPU or TPU)
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@superbobry @sbodenstein