Qualcomm AI Engine Direct - issue fix #2#14378
Conversation
- pytorch#14048 > add quantized test case with GLU decomposition - pytorch#14049 > add e2e example where constant expansion is applied - pytorch#14050 > add e2e example and source transform for 6D operation - pytorch#14051 > add e2e example and complement missed annotation - pytorch#14052 > add e2e example and dedicated passe for 6D partition
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14378
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit d14e489 with merge base 56659e4 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This PR needs a
|
|
Thanks for the fix! I think we may need some logics to block lowering rank-6 shape, because users may not know how to do it themselves |
|
@haowhsu-quic Do you want to include this in release/1.0 branch? If so, please follow instructions in #14288 Similar to #14328 |
### Summary - pytorch#14048 > add quantized test case with GLU decomposition - pytorch#14049 > add e2e example where constant expansion is applied - pytorch#14050 > add e2e example and source transform for 6D operation - pytorch#14051 > add e2e example and complement missed annotation - pytorch#14052 > add e2e example and dedicated passe for 6D partition Fixes pytorch#14048 Fixes pytorch#14049 Fixes pytorch#14050 Fixes pytorch#14051 Fixes pytorch#14052 ### Test plan MATRIX = {convnext_small, maxvit_t, swin_v2_t, vit_b_16} ```bash python backends/qualcomm/tests/test_qnn_delegate.py TestExampleOssScript.test_${MATRIX} -b build-android/ -m SM8750 -s $SN -a /path/to/test_artifacts/ -i /path/to/imagenet_1k/imagenet-mini/val -r . ``` ```bash python backends/qualcomm/tests/test_qnn_delegate.py TestQuantizedModel.test_qnn_backend_conformer -b build-android/ -m SM8750 -s $SN -a /path/to/test_artifacts/ ```
|
@pytorchbot cherry-pick --onto release/1.0 -c regression |
### Summary - #14048 > add quantized test case with GLU decomposition - #14049 > add e2e example where constant expansion is applied - #14050 > add e2e example and source transform for 6D operation - #14051 > add e2e example and complement missed annotation - #14052 > add e2e example and dedicated passe for 6D partition Fixes #14048 Fixes #14049 Fixes #14050 Fixes #14051 Fixes #14052 ### Test plan MATRIX = {convnext_small, maxvit_t, swin_v2_t, vit_b_16} ```bash python backends/qualcomm/tests/test_qnn_delegate.py TestExampleOssScript.test_${MATRIX} -b build-android/ -m SM8750 -s $SN -a /path/to/test_artifacts/ -i /path/to/imagenet_1k/imagenet-mini/val -r . ``` ```bash python backends/qualcomm/tests/test_qnn_delegate.py TestQuantizedModel.test_qnn_backend_conformer -b build-android/ -m SM8750 -s $SN -a /path/to/test_artifacts/ ``` (cherry picked from commit 2b54a19)
Cherry picking #14378The cherry pick PR is at #14947 and it is recommended to link a regression cherry pick PR with an issue. The following tracker issues are updated: Details for Dev Infra teamRaised by workflow job |
### Summary - pytorch#14048 > add quantized test case with GLU decomposition - pytorch#14049 > add e2e example where constant expansion is applied - pytorch#14050 > add e2e example and source transform for 6D operation - pytorch#14051 > add e2e example and complement missed annotation - pytorch#14052 > add e2e example and dedicated passe for 6D partition Fixes pytorch#14048 Fixes pytorch#14049 Fixes pytorch#14050 Fixes pytorch#14051 Fixes pytorch#14052 ### Test plan MATRIX = {convnext_small, maxvit_t, swin_v2_t, vit_b_16} ```bash python backends/qualcomm/tests/test_qnn_delegate.py TestExampleOssScript.test_${MATRIX} -b build-android/ -m SM8750 -s $SN -a /path/to/test_artifacts/ -i /path/to/imagenet_1k/imagenet-mini/val -r . ``` ```bash python backends/qualcomm/tests/test_qnn_delegate.py TestQuantizedModel.test_qnn_backend_conformer -b build-android/ -m SM8750 -s $SN -a /path/to/test_artifacts/ ```
Summary
Fixes #14048
Fixes #14049
Fixes #14050
Fixes #14051
Fixes #14052
Test plan
MATRIX = {convnext_small, maxvit_t, swin_v2_t, vit_b_16}
python backends/qualcomm/tests/test_qnn_delegate.py TestQuantizedModel.test_qnn_backend_conformer -b build-android/ -m SM8750 -s $SN -a /path/to/test_artifacts/