Support BFloat16 in exir #14164
Merged
Support BFloat16 in exir #14164
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
manuelcandales
requested review from
JacobSzwejbka and
larryliu0820
as code owners
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14164
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 Cancelled Job, 4 Unrelated FailuresAs of commit bbf3095 with merge base 47acc87 ( CANCELLED JOB - The following job was cancelled. Please retry:
FLAKY - The following job failed but was likely due to flakiness present on trunk:
BROKEN TRUNK - The following jobs failed but was 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. |
meta-cla
bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D82129165 |
manuelcandales
added
the
release notes: exir
JacobSzwejbka
approved these changes
Sep 10, 2025
manuelcandales
added a commit
to manuelcandales/executorch-1
that referenced
this pull request
Sep 10, 2025
Summary: This diff adds support for BFloat16 dtype in ExecuTorch's exir dialect by updating the type system and operator constraints. Previously, BFloat16 inputs required disabling IR validity checks with `_check_ir_validity=False` to work around the lack of proper type system support. The changes include: - Adding `torch.bfloat16: "BFloat16"` mapping in the supported dtypes configuration - Updating edge.yaml to include BFloat16 anywhere that Half is supported Reviewed By: JacobSzwejbka Differential Revision: D82129165
manuelcandales
force-pushed
the
export-D82129165
branch
from
b10217a to
9c5d0b4
Compare
|
This pull request was exported from Phabricator. Differential Revision: D82129165 |
manuelcandales
added a commit
to manuelcandales/executorch-1
that referenced
this pull request
Sep 10, 2025
Summary: This diff adds support for BFloat16 dtype in ExecuTorch's exir dialect by updating the type system and operator constraints. Previously, BFloat16 inputs required disabling IR validity checks with `_check_ir_validity=False` to work around the lack of proper type system support. The changes include: - Adding `torch.bfloat16: "BFloat16"` mapping in the supported dtypes configuration - Updating edge.yaml to include BFloat16 anywhere that Half is supported Reviewed By: JacobSzwejbka Differential Revision: D82129165
manuelcandales
force-pushed
the
export-D82129165
branch
from
9c5d0b4 to
c45d811
Compare
|
This pull request was exported from Phabricator. Differential Revision: D82129165 |
manuelcandales
force-pushed
the
export-D82129165
branch
from
c45d811 to
6f08836
Compare
manuelcandales
added a commit
to manuelcandales/executorch-1
that referenced
this pull request
Sep 10, 2025
Summary: This diff adds support for BFloat16 dtype in ExecuTorch's exir dialect by updating the type system and operator constraints. Previously, BFloat16 inputs required disabling IR validity checks with `_check_ir_validity=False` to work around the lack of proper type system support. The changes include: - Adding `torch.bfloat16: "BFloat16"` mapping in the supported dtypes configuration - Updating edge.yaml to include BFloat16 anywhere that Half is supported Reviewed By: JacobSzwejbka Differential Revision: D82129165
|
This pull request was exported from Phabricator. Differential Revision: D82129165 |
Summary: This diff adds support for BFloat16 dtype in ExecuTorch's exir dialect by updating the type system and operator constraints. Previously, BFloat16 inputs required disabling IR validity checks with `_check_ir_validity=False` to work around the lack of proper type system support. The changes include: - Adding `torch.bfloat16: "BFloat16"` mapping in the supported dtypes configuration - Updating edge.yaml to include BFloat16 anywhere that Half is supported Reviewed By: JacobSzwejbka Differential Revision: D82129165
manuelcandales
force-pushed
the
export-D82129165
branch
from
6f08836 to
bbf3095
Compare
|
This pull request was exported from Phabricator. Differential Revision: D82129165 |
StrycekSimon
pushed a commit
to nxp-upstream/executorch
that referenced
this pull request
Sep 23, 2025
Differential Revision: D82129165 Pull Request resolved: pytorch#14164
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary:
This diff adds support for BFloat16 dtype in ExecuTorch's exir dialect by updating the type system and operator constraints.
Previously, BFloat16 inputs required disabling IR validity checks with
_check_ir_validity=Falseto work around the lack of proper type system support.The changes include:
torch.bfloat16: "BFloat16"mapping in the supported dtypes configurationDifferential Revision: D82129165