Arm backend: support int16 and int32 output tables. #9359
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
Erik-Lundell
added
partner: arm
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/9359
Note: Links to docs will display an error until the docs builds have been completed. ❌ 5 New Failures, 1 Unrelated FailureAs of commit 00f590f with merge base 95d7cce ( NEW FAILURES - The following jobs have 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. |
facebook-github-bot
added
the
CLA Signed
digantdesai
approved these changes
Mar 21, 2025
Erik-Lundell
force-pushed
the
int16-tables
branch
from
e7989ad to
293dcb5
Compare
|
Thanks for the detailed review Digant! :) |
Rsqrt is in the pipeline, but we want to implement it as a special case of pow so we need to get pow done first |
Change insert_table_ops to support int16 table generation. Insert rescale in insert_table_ops if needed. Remove guard for int16 on insert_rescales. The new test shows how the quantizer can be configured to change the quantization of Sigmoid. Signed-off-by: Erik Lundell <[email protected]> Change-Id: Ice9e1f2c2db089191df3bd1a22eff0bfe3048520
Erik-Lundell
force-pushed
the
int16-tables
branch
from
293dcb5 to
00f590f
Compare
DannyYuyang-quic
pushed a commit
to CodeLinaro/executorch
that referenced
this pull request
Apr 2, 2025
Change insert_table_ops to support int16 table generation. Insert rescale in insert_table_ops if needed. Remove guard for int16 on insert_rescales. The new test shows how the quantizer can be configured to change the quantization of Sigmoid. cc @digantdesai @freddan80 @per @zingo @oscarandersson8218 Signed-off-by: Erik Lundell <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Change insert_table_ops to support int16 table generation. Insert rescale in insert_table_ops if needed.
Remove guard for int16 on insert_rescales.
The new test shows how the quantizer can be configured to change the quantization of Sigmoid.
cc @digantdesai @freddan80 @per @zingo @oscarandersson8218