Update addmm int16 for Ethos-U85 #14714
Merged
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14714
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 6e5764c with merge base 53ccfd0 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
|
@pytorchbot label "release notes: none" |
pytorch-bot
bot
added
the
release notes: none
3l1
added a commit
that referenced
this pull request
Oct 1, 2025
Summary: Adjust op_bmm to allow int16 types with int48 output buffer Note: I am rescaling back to the original int16 dtype output. This is obviously dangerous if done without a properly calibrated quantization parameter, but this is our base assumption. Differential Revision: D83627934
facebook-github-bot
pushed a commit
that referenced
this pull request
Oct 1, 2025
Summary: Adjust op_bmm to allow int16 types with int48 output buffer Note: I am rescaling back to the original int16 dtype output. This is obviously dangerous if done without a properly calibrated quantization parameter, but this is our base assumption. Differential Revision: D83627934
facebook-github-bot
force-pushed
the
export-D83627934
branch
from
3691a40 to
56b10c4
Compare
digantdesai
approved these changes
Oct 2, 2025
facebook-github-bot
pushed a commit
that referenced
this pull request
Oct 2, 2025
Summary: Adjust op_bmm to allow int16 types with int48 output buffer Note: I am rescaling back to the original int16 dtype output. This is obviously dangerous if done without a properly calibrated quantization parameter, but this is our base assumption. Reviewed By: digantdesai Differential Revision: D83627934
facebook-github-bot
force-pushed
the
export-D83627934
branch
from
56b10c4 to
cbc8093
Compare
facebook-github-bot
pushed a commit
that referenced
this pull request
Oct 3, 2025
Summary: Adjust op_bmm to allow int16 types with int48 output buffer Note: I am rescaling back to the original int16 dtype output. This is obviously dangerous if done without a properly calibrated quantization parameter, but this is our base assumption. Reviewed By: digantdesai Differential Revision: D83627934
facebook-github-bot
force-pushed
the
export-D83627934
branch
from
cbc8093 to
ce36955
Compare
Summary: Adjust op_bmm to allow int16 types with int48 output buffer Note: I am rescaling outputs back to the original int16 dtype output. This is obviously dangerous if done without a properly calibrated quantization parameter, but this is our base assumption. bypass-github-export-checks bypass-github-pytorch-ci-checks bypass-github-executorch-ci-checks Reviewed By: digantdesai Differential Revision: D83627934
facebook-github-bot
force-pushed
the
export-D83627934
branch
from
ce36955 to
6e5764c
Compare
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:
Adjust op_bmm to allow int16 types with int48 output buffer
Note: I am rescaling back to the original int16 dtype output. This is obviously dangerous if done without a properly calibrated quantization parameter, but this is our base assumption.
Differential Revision: D83627934