Add cortex_m MVE/Helium int16 quantize/dequantize support (#19218)#19218
Merged
meta-codesync[bot] merged 1 commit intomainfrom Apr 30, 2026
Merged
Add cortex_m MVE/Helium int16 quantize/dequantize support (#19218)#19218meta-codesync[bot] merged 1 commit intomainfrom
meta-codesync[bot] merged 1 commit intomainfrom
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19218
Note: Links to docs will display an error until the docs builds have been completed. ⏳ 1 Pending, 2 Unrelated FailuresAs of commit f3fe5c6 with merge base e84a418 ( BROKEN TRUNK - The following jobs 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. |
meta-cla
Bot
added
the
CLA Signed
Contributor
|
@3l1 has exported this pull request. If you are a Meta employee, you can view the originating Diff in D103129855. |
This PR needs a
|
meta-codesync
Bot
changed the title
meta-codesync Bot
pushed a commit
that referenced
this pull request
Apr 30, 2026
Summary: Adds MVE-vectorized int16 (Short) paths to the Cortex-M ExecuTorch quant ops, plus the AoT partitioner update so the ARM partitioner rewrites int16 quantized_decomposed::* to cortex_m::*. Previously cortex_m only handled int8 — int16 quant ops fell through to the portable scalar fallback (no MVE on Cortex-M55, since the portable path is gated on __aarch64__ || __ARM_NEON__ which Cortex-M55 has neither of). Differential Revision: D103129855
meta-codesync
Bot
force-pushed
the
export-D103129855
branch
from
6b9ce08 to
a27f25f
Compare
meta-codesync Bot
pushed a commit
that referenced
this pull request
Apr 30, 2026
Summary: Adds MVE-vectorized int16 (Short) paths to the Cortex-M ExecuTorch quant ops, plus the AoT partitioner update so the ARM partitioner rewrites int16 quantized_decomposed::* to cortex_m::*. Previously cortex_m only handled int8 — int16 quant ops fell through to the portable scalar fallback. Differential Revision: D103129855
meta-codesync
Bot
force-pushed
the
export-D103129855
branch
from
a27f25f to
89e6708
Compare
meta-codesync Bot
pushed a commit
that referenced
this pull request
Apr 30, 2026
Summary: Adds MVE-vectorized int16 (Short) paths to the Cortex-M ExecuTorch quant ops, so the ARM partitioner rewrites int16 quantized_decomposed::* to cortex_m::*. Previously cortex_m only handled int8 — int16 quant ops fell through to the portable scalar fallback. Differential Revision: D103129855
meta-codesync
Bot
force-pushed
the
export-D103129855
branch
from
89e6708 to
5cea79a
Compare
Summary: Adds MVE-vectorized int16 (Short) paths to the Cortex-M ExecuTorch quant ops, so the ARM partitioner rewrites int16 quantized_decomposed::* to cortex_m::*. Previously cortex_m only handled int8 — int16 quant ops fell through to the portable scalar fallback. Differential Revision: D103129855
meta-codesync
Bot
force-pushed
the
export-D103129855
branch
from
5cea79a to
f3fe5c6
Compare
3l1
added
the
partner: arm
rascani
approved these changes
Apr 30, 2026
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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:
Adds MVE-vectorized int16 (Short) paths to the Cortex-M ExecuTorch quant ops, so the ARM partitioner rewrites int16 quantized_decomposed::* to cortex_m::*. Previously cortex_m only handled int8 — int16 quant ops fell through to the portable scalar fallback.
Differential Revision: D103129855
cc @digantdesai @freddan80 @per @zingo @oscarandersson8218 @mansnils @Sebastian-Larsson @robell