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.

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

Add SupportedTensorDtypes::{BOOL,REALH} #9584

Open
wants to merge 11 commits into
base: gh/swolchok/382/head
Choose a base branch
from

Conversation

swolchok
Copy link
Contributor

@swolchok swolchok commented Mar 25, 2025

The purpose of REALH will be to support the current use cases of unary_ufunc_realh. (Maybe we should just change them to support BF16?)

swolchok added 10 commits March 18, 2025 17:32
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
@swolchok swolchok requested a review from GregoryComer as a code owner March 25, 2025 17:05
Copy link

pytorch-bot bot commented Mar 25, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/9584

Note: Links to docs will display an error until the docs builds have been completed.

❌ 1 New Failure, 1 Unrelated Failure

As of commit f934bc0 with merge base 644b7dd (image):

NEW FAILURE - The following job has failed:

BROKEN TRUNK - The following job failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@@ -23,10 +23,14 @@ bool check_tensor_dtype(
return executorch::runtime::tensor_is_realhbbf16_type(t);
case SupportedTensorDtypes::REALHBF16:
return executorch::runtime::tensor_is_realhbf16_type(t);
case SupportedTensorDtypes::REALH:
Copy link
Contributor

@JacobSzwejbka JacobSzwejbka Mar 25, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

what is the h in realh? half?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yes, it matches the naming scheme in

#define ET_SWITCH_REALH_TYPES(TYPE, CONTEXT, NAME, CTYPE_ALIAS, ...) \

@swolchok swolchok temporarily deployed to upload-benchmark-results March 25, 2025 17:22 — with GitHub Actions Inactive
@swolchok swolchok temporarily deployed to upload-benchmark-results March 25, 2025 17:26 — with GitHub Actions Inactive
@swolchok swolchok changed the base branch from gh/swolchok/386/head to gh/swolchok/382/head March 25, 2025 18:12
[ghstack-poisoned]
@swolchok
Copy link
Contributor Author

probably we want to skip adding REALH and just replace it with REALHBF16 in subseqeuent diffs

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants