Add a16w8 per-op test for split by christine-long-meta · Pull Request #19600 · pytorch/executorch

christine-long-meta · 2026-05-14T16:49:00Z

Summary:
Add int16 activation / int8 weight (a16w8) quantization tests for aten.split on Ethos-U55 and Ethos-U85.

Changes

Add a16w8_split_test_parameters dict with 3 test configurations covering 1D, 2D, and 3D splits along different axes
Add test_split_a16w8_u55_INT using EthosU55PipelineINT with a16w8_quantization=True, symmetric_io_quantization=True, qtol=128, epsilon=2**-16
Add test_split_a16w8_u85_INT using EthosU85PipelineINT with same kwargs
Register ops/test_split.py in fbcode/ and xplat/ targets.bzl

bypass-pytorch-oss-checks

Differential Revision: D104533281

pytorch-bot · 2026-05-14T16:49:04Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19600

📄 Preview Python docs built from this PR

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

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

Run pull request jobs on OSDC runners in shadow mode

❌ 1 New Failure, 3 Cancelled Jobs, 38 Pending

As of commit f550f2b with merge base 58b4f26 ():

NEW FAILURE - The following job has failed:

trunk / test-arm-backend-ethos-u (test_pytest_ops_ethos_u85) / linux-job (gh)
RuntimeError: Command docker exec -t 8972cb96ffb350c5062bbcb1cd55b6369a29f0346d0af31a01b1b2bcef259c83 /exec failed with exit code 1

CANCELLED JOBS - The following jobs were cancelled. Please retry:

Test CoreML Backend / test-coreml / test-backend-macos (coreml, models) / macos-job (gh)
Test CoreML Backend / test-coreml / test-backend-macos (coreml, operators) / macos-job (gh)
Test XNNPACK Backend / test-xnnpack / package-golden-artifacts (gh)
##[error]The operation was canceled.

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

pytorch-bot · 2026-05-14T16:49:22Z

~~Workflows were awaiting approval.~~ CI has now been triggered for the ciflow labels on this PR.

github-actions · 2026-05-14T16:50:23Z

This PR needs a `release notes:` label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

Summary: Add int16 activation / int8 weight (a16w8) quantization tests for `aten.split` on Ethos-U55 and Ethos-U85. ## Changes - Add `a16w8_split_test_parameters` dict with 3 test configurations covering 1D, 2D, and 3D splits along different axes - Add `test_split_a16w8_u55_INT` using `EthosU55PipelineINT` with `a16w8_quantization=True, symmetric_io_quantization=True, qtol=128, epsilon=2**-16` - Add `test_split_a16w8_u85_INT` using `EthosU85PipelineINT` with same kwargs - Register `ops/test_split.py` in `fbcode/` and `xplat/` `targets.bzl` bypass-pytorch-oss-checks Differential Revision: D104533281

meta-codesync · 2026-05-14T16:54:34Z

@christine-long-meta has exported this pull request. If you are a Meta employee, you can view the originating Diff in D104533281.

Summary: Pull Request resolved: pytorch#19600 Add int16 activation / int8 weight (a16w8) quantization tests for `aten.split` on Ethos-U55 and Ethos-U85. ## Changes - Add `a16w8_split_test_parameters` dict with 3 test configurations covering 1D, 2D, and 3D splits along different axes - Add `test_split_a16w8_u55_INT` using `EthosU55PipelineINT` with `a16w8_quantization=True, symmetric_io_quantization=True, qtol=128, epsilon=2**-16` - Add `test_split_a16w8_u85_INT` using `EthosU85PipelineINT` with same kwargs - Register `ops/test_split.py` in `fbcode/` and `xplat/` `targets.bzl` bypass-pytorch-oss-checks Differential Revision: D104533281

Summary: Add int16 activation / int8 weight (a16w8) quantization tests for `aten.exp` on Ethos-U55 and Ethos-U85. ## Context The `exp` op is part of the softmax decomposition (`softmax(x) = exp(x) / sum(exp(x))`), which is used in the attention mechanism of EMG2Pose Conformer models. This op was identified as the root cause of the U85 SNR regression investigated in SEV T267939669 — without dedicated a16w8 per-op coverage, the numerics issue was only visible at the full-model level. Adding per-op tests allows us to catch int16 precision regressions at the operator granularity before they propagate to end-to-end model accuracy. ## Changes - Add `a16w8_exp_test_parameters` dict with 3 test configurations covering rank-1, rank-2, and rank-3 tensors - Add `test_exp_a16w8_u55_INT` using `EthosU55PipelineINT` with `a16w8_quantization=True, symmetric_io_quantization=True, qtol=128, epsilon=2**-16` - Add `test_exp_a16w8_u85_INT` using `EthosU85PipelineINT` with same kwargs - Register `ops/test_exp.py` in `fbcode/` and `xplat/` `targets.bzl` bypass-pytorch-oss-checks Differential Revision: D104532358

Summary: Add int16 activation / int8 weight (a16w8) quantization tests for `aten.reciprocal` on Ethos-U55 and Ethos-U85. ## Context The `reciprocal` op is the second half of the softmax decomposition (`softmax(x) = exp(x) * reciprocal(sum(exp(x)))`), paired with `exp`. Together they form the attention mechanism in EMG2Pose Conformer models. Like `exp`, this op was implicated in the U85 SNR regression (SEV T267939669) — the division-by-reciprocal path can amplify quantization error when the denominator is itself quantized at int16. Adding dedicated a16w8 coverage isolates reciprocal numerics from the rest of the softmax pipeline. ## Changes - Add `a16w8_reciprocal_test_parameters` dict with 3 test configurations covering rank-1, rank-2, and rank-3 tensors (all shifted by +0.1 to avoid division near zero) - Add `test_reciprocal_a16w8_u55_INT` using `EthosU55PipelineINT` with `a16w8_quantization=True, symmetric_io_quantization=True, qtol=128, epsilon=2**-16` - Add `test_reciprocal_a16w8_u85_INT` using `EthosU85PipelineINT` with same kwargs - Register `ops/test_reciprocal.py` in `fbcode/` and `xplat/` `targets.bzl` bypass-pytorch-oss-checks Differential Revision: D104532357

Summary: Add int16 activation / int8 weight (a16w8) quantization tests for `aten.mean.dim` on Ethos-U55 and Ethos-U85. ## Changes - Add `a16w8_mean_test_parameters` dict with 11 test configurations covering keepdim/no-keepdim, positive/negative dims, dim=None, and ranks 1-4 - Add `test_mean_dim_a16w8_u55_INT` using `EthosU55PipelineINT` with `a16w8_quantization=True, symmetric_io_quantization=True, qtol=128, epsilon=2**-16` - Add `test_mean_dim_a16w8_u85_INT` using `EthosU85PipelineINT` with same kwargs - Register `ops/test_mean_dim.py` in `fbcode/` and `xplat/` `targets.bzl` bypass-pytorch-oss-checks Differential Revision: D104532361

Summary: Add int16 activation / int8 weight (a16w8) quantization tests for `aten.var` on Ethos-U55 and Ethos-U85. ## Changes - Add `a16w8_var_test_parameters` dict with 4 test configurations covering keepdim/no-keepdim and correction values 0, 0.5, and 1 - Add `test_var_a16w8_u55_INT` using `EthosU55PipelineINT` with `a16w8_quantization=True, symmetric_io_quantization=True, qtol=128, epsilon=2**-16` - Add `test_var_a16w8_u85_INT` using `EthosU85PipelineINT` with same kwargs - Register `ops/test_var.py` in `fbcode/` and `xplat/` `targets.bzl` bypass-pytorch-oss-checks Differential Revision: D104532362

Summary: Add int16 activation / int8 weight (a16w8) quantization tests for `aten.conv1d` on Ethos-U55 and Ethos-U85. ## Changes - Add `test_conv1d_a16w8_u55_INT` using `EthosU55PipelineINT` with `a16w8_quantization=True, symmetric_io_quantization=True, qtol=1, epsilon=2**-16`, reusing existing `test_data_INT` parameters - Add `test_conv1d_a16w8_u85_INT` using `EthosU85PipelineINT` with same kwargs - Register `ops/test_conv1d.py` in `fbcode/` and `xplat/` `targets.bzl` bypass-pytorch-oss-checks Differential Revision: D104532360

Summary: Add int16 activation / int8 weight (a16w8) quantization tests for `aten.gelu` on Ethos-U55 and Ethos-U85. ## Changes - Add `a16w8_gelu_test_parameters` dict with 3 test configurations covering rank-1, rank-2, and rank-3 tensors - Add `test_gelu_a16w8_u55_INT` using `EthosU55PipelineINT` with `a16w8_quantization=True, symmetric_io_quantization=True, qtol=128, epsilon=2**-16` - Add `test_gelu_a16w8_u85_INT` using `EthosU85PipelineINT` with same kwargs - Register `ops/test_gelu.py` in `fbcode/` and `xplat/` `targets.bzl` bypass-pytorch-oss-checks Differential Revision: D104532359

Summary: Add int16 activation / int8 weight (a16w8) quantization tests for `aten.bmm` on Ethos-U55 and Ethos-U85. ## Changes - Add `a16w8_bmm_test_parameters` dict with 5 test configurations covering same-shape, different-shape, rectangular, batch-10, and negative-value tensors - Add `test_bmm_a16w8_u55_INT` using `EthosU55PipelineINT` with `a16w8_quantization=True, symmetric_io_quantization=True, qtol=128, epsilon=2**-16` - Add `test_bmm_a16w8_u85_INT` using `EthosU85PipelineINT` with same kwargs - Remove unused `aten_op_mm` and `exir_op_mm` variables - Register `ops/test_bmm.py` in `fbcode/` and `xplat/` `targets.bzl` bypass-pytorch-oss-checks Differential Revision: D104532363

Summary: Add int16 activation / int8 weight (a16w8) quantization tests for `aten.split` on Ethos-U55 and Ethos-U85. ## Changes - Add `a16w8_split_test_parameters` dict with 3 test configurations covering 1D, 2D, and 3D splits along different axes - Add `test_split_a16w8_u55_INT` using `EthosU55PipelineINT` with `a16w8_quantization=True, symmetric_io_quantization=True, qtol=128, epsilon=2**-16` - Add `test_split_a16w8_u85_INT` using `EthosU85PipelineINT` with same kwargs - Register `ops/test_split.py` in `fbcode/` and `xplat/` `targets.bzl` bypass-pytorch-oss-checks Differential Revision: D104533281

christine-long-meta requested a review from digantdesai as a code owner May 14, 2026 16:49

github-actions Bot added ciflow/trunk module: arm Issues related to arm backend labels May 14, 2026

meta-cla Bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label May 14, 2026

meta-codesync Bot added fb-exported meta-exported labels May 14, 2026

christine-long-meta force-pushed the export-D104533281 branch from 2022aff to 88e9821 Compare May 14, 2026 16:53

meta-codesync Bot changed the title ~~Add a16w8 per-op test for split~~ Add a16w8 per-op test for split (#19600) May 14, 2026

christine-long-meta force-pushed the export-D104533281 branch from 88e9821 to f550f2b Compare May 14, 2026 20:51

christine-long-meta added 8 commits May 14, 2026 14:22

meta-codesync Bot changed the title ~~Add a16w8 per-op test for split (#19600)~~ Add a16w8 per-op test for split May 14, 2026

christine-long-meta force-pushed the export-D104533281 branch from f550f2b to 8fd5ef8 Compare May 14, 2026 21:23

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Add a16w8 per-op test for split#19600

Add a16w8 per-op test for split#19600
christine-long-meta wants to merge 8 commits into
pytorch:mainfrom
christine-long-meta:export-D104533281

christine-long-meta commented May 14, 2026 •

edited by meta-codesync Bot

Loading

Uh oh!

pytorch-bot Bot commented May 14, 2026 •

edited

Loading

Uh oh!

pytorch-bot Bot commented May 14, 2026 •

edited

Loading

Uh oh!

github-actions Bot commented May 14, 2026

Uh oh!

meta-codesync Bot commented May 14, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Conversation

christine-long-meta commented May 14, 2026 • edited by meta-codesync Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Changes

Uh oh!

pytorch-bot Bot commented May 14, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19600

❗ 1 Active SEVs

❌ 1 New Failure, 3 Cancelled Jobs, 38 Pending

Uh oh!

pytorch-bot Bot commented May 14, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

github-actions Bot commented May 14, 2026

This PR needs a release notes: label

Uh oh!

meta-codesync Bot commented May 14, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

christine-long-meta commented May 14, 2026 •

edited by meta-codesync Bot

Loading

pytorch-bot Bot commented May 14, 2026 •

edited

Loading

pytorch-bot Bot commented May 14, 2026 •

edited

Loading

This PR needs a `release notes:` label