Add a16w8 per-op test for bmm (#19599)#19599
Open
christine-long-meta wants to merge 4 commits into
Open
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19599
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 Cancelled JobAs of commit 2381b0f with merge base 42d87c4 ( CANCELLED JOB - The following job was cancelled. Please retry:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
christine-long-meta
force-pushed
the
export-D104532363
branch
from
c0c8f38 to
1854072
Compare
meta-cla
Bot
added
the
CLA Signed
|
|
This PR needs a
|
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.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
christine-long-meta
force-pushed
the
export-D104532363
branch
from
1854072 to
d5349b3
Compare
meta-codesync
Bot
changed the title
christine-long-meta
force-pushed
the
export-D104532363
branch
from
d5349b3 to
77a9a41
Compare
Contributor
|
@christine-long-meta has exported this pull request. If you are a Meta employee, you can view the originating Diff in D104532363. |
1 similar comment
Contributor
|
@christine-long-meta has exported this pull request. If you are a Meta employee, you can view the originating Diff in D104532363. |
christine-long-meta
added a commit
to christine-long-meta/executorch
that referenced
this pull request
May 14, 2026
Summary: Pull Request resolved: pytorch#19599 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
christine-long-meta
force-pushed
the
export-D104532363
branch
2 times, most recently
from
6a8da35 to
71103e7
Compare
meta-codesync
Bot
changed the title
Summary: Add int16 activation / int8 weight (a16w8) quantization tests for `aten.var` on Ethos-U55 and Ethos-U85. ## Changes - Add `test_parameters_ethosu` class attribute to `Var` with 2 test configurations (4D tensors with correction=0 and correction=1) - Switch existing `test_var_dim_u55_INT_no_dim` and `test_var_dim_u85_INT_no_dim` from `Var.test_parameters` to `Var.test_parameters_ethosu` for Ethos-U compatible tensor shapes - Add `test_var_a16w8_u55_INT` using `EthosU55PipelineINT` with `a16w8_quantization=True, symmetric_io_quantization=True` - Add `test_var_a16w8_u85_INT` using `EthosU85PipelineINT` with same kwargs - Register `ops/test_var.py` in `fbcode/` and `xplat/` `targets.bzl` 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`, 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` Reviewed By: Ninja91 Differential Revision: D104532360
Summary: Add int16 activation / int8 weight (a16w8) quantization tests for `aten.gelu` on Ethos-U55 and Ethos-U85. ## Changes - Add `test_gelu_a16w8_u55_INT` using `EthosU55PipelineINT` with `a16w8_quantization=True, symmetric_io_quantization=True, qtol=128, epsilon=2**-16`, reusing existing `Gelu.test_data` parameters (12 test configurations covering both \`none\` and \`tanh\` approximation modes) - 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 `OpNotSupportedPipeline` to verify that bmm with INT16 inputs is correctly rejected on U55 (which does not support bmm with int16) - Add `test_bmm_a16w8_u85_INT` using `EthosU85PipelineINT` with `a16w8_quantization=True, symmetric_io_quantization=True` - Remove unused `aten_op_mm` and `exir_op_mm` variables - Register `ops/test_bmm.py` in `fbcode/` and `xplat/` `targets.bzl` Differential Revision: D104532363
christine-long-meta
force-pushed
the
export-D104532363
branch
from
71103e7 to
2381b0f
Compare
meta-codesync
Bot
changed the title
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.bmmon Ethos-U55 and Ethos-U85.Changes
a16w8_bmm_test_parametersdict with 5 test configurations covering same-shape, different-shape, rectangular, batch-10, and negative-value tensorstest_bmm_a16w8_u55_INTusingOpNotSupportedPipelineto verify that bmm with INT16 inputs is correctly rejected on U55 (which does not support bmm with int16)test_bmm_a16w8_u85_INTusingEthosU85PipelineINTwitha16w8_quantization=True, symmetric_io_quantization=Trueaten_op_mmandexir_op_mmvariablesops/test_bmm.pyinfbcode/andxplat/targets.bzlDifferential Revision: D104532363