Add a16w8 per-op test for mean_dim (#19594)#19594
Open
christine-long-meta wants to merge 3 commits into
Open
Conversation
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19594
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ❌ 1 New FailureAs of commit cccb394 with merge base 58b4f26 ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
|
meta-cla
Bot
added
the
CLA Signed
Contributor
|
@christine-long-meta has exported this pull request. If you are a Meta employee, you can view the originating Diff in D104532361. |
christine-long-meta
force-pushed
the
export-D104532361
branch
from
db30c66 to
744487a
Compare
This PR needs a
|
christine-long-meta
force-pushed
the
export-D104532361
branch
from
744487a to
ce874b4
Compare
meta-codesync
Bot
changed the title
christine-long-meta
force-pushed
the
export-D104532361
branch
2 times, most recently
from
744487a to
b79321f
Compare
christine-long-meta
added a commit
to christine-long-meta/executorch
that referenced
this pull request
May 14, 2026
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
christine-long-meta
force-pushed
the
export-D104532361
branch
3 times, most recently
from
e7d90e2 to
37c98c1
Compare
christine-long-meta
added a commit
to christine-long-meta/executorch
that referenced
this pull request
May 14, 2026
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
christine-long-meta
force-pushed
the
export-D104532361
branch
2 times, most recently
from
b79321f to
3350584
Compare
Contributor
|
@christine-long-meta has exported this pull request. If you are a Meta employee, you can view the originating Diff in D104532361. |
christine-long-meta
added a commit
to christine-long-meta/executorch
that referenced
this pull request
May 14, 2026
Summary: Pull Request resolved: pytorch#19594 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
christine-long-meta
force-pushed
the
export-D104532361
branch
4 times, most recently
from
7bb5c56 to
d8dea29
Compare
meta-codesync
Bot
changed the title
christine-long-meta
force-pushed
the
export-D104532361
branch
from
d8dea29 to
0733afe
Compare
christine-long-meta
added a commit
to christine-long-meta/executorch
that referenced
this pull request
May 14, 2026
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: Pull Request resolved: pytorch#19594 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
meta-codesync
Bot
changed the title
christine-long-meta
force-pushed
the
export-D104532361
branch
from
0733afe to
cccb394
Compare
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
1 participant
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:
Add int16 activation / int8 weight (a16w8) quantization tests for
aten.mean.dimon Ethos-U55 and Ethos-U85.Changes
a16w8_mean_test_parametersdict with 11 test configurations covering keepdim/no-keepdim, positive/negative dims, dim=None, and ranks 1-4test_mean_dim_a16w8_u55_INTusingEthosU55PipelineINTwitha16w8_quantization=True, symmetric_io_quantization=True, qtol=128, epsilon=2**-16test_mean_dim_a16w8_u85_INTusingEthosU85PipelineINTwith same kwargsops/test_mean_dim.pyinfbcode/andxplat/targets.bzlbypass-pytorch-oss-checks
Differential Revision: D104532361