Qualcomm AI Engine Direct - Enable Example/OSS models on GPU backend #16425

chenweng-quic · 2026-01-02T08:38:30Z

Summary

Update model scripts for GPU backend.

Succeed

albert
bert
conv_former
convnext_small
cvt
deit
distilbert
dit
edsr
fbnet
focalnet
gMLP
inception_v3
inception_v4
maxvit_t
mobilevit_v1
mobilenet_v2
regnet
retinanet
torchvision_vit

Validation failed

dino_v2
efficientnet
efficientSAM
esrgan
eurobert
mobilevit_v2
squeezenet
ssd300_vgg16
swin_v2_t
t5
whisper

Finalization failed

fastvit

Has accuracy issue

pvt
roberta
swin_transformer
vit_b_16
mobilenet_v3

Test plan

python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_albert --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --sentence_dataset /local/mnt/workspace/chenweng/executorch/wikisent2.txt
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_bert --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --sentence_dataset /local/mnt/workspace/chenweng/executorch/wikisent2.txt
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_conv_former --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --image_dataset /local/mnt/workspace/chenweng/executorch/imagenet-mini/val
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_convnext_small --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --image_dataset /local/mnt/workspace/chenweng/executorch/imagenet-mini/val
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_cvt --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --image_dataset /local/mnt/workspace/chenweng/executorch/imagenet-mini/val
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_deit --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --image_dataset /local/mnt/workspace/chenweng/executorch/imagenet-mini/val
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_dino_v2 --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --image_dataset /local/mnt/workspace/chenweng/executorch/imagenet-mini/val
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_distilbert --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --sentence_dataset /local/mnt/workspace/chenweng/executorch/wikisent2.txt
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_dit --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_efficientnet --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --image_dataset /local/mnt/workspace/chenweng/executorch/imagenet-mini/val
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_efficientSAM --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --image_dataset /local/mnt/workspace/chenweng/executorch/imagenet-mini/val --pretrained_weight /local/mnt/workspace/chenweng/executorch/EfficientSAM/weights/efficient_sam_vitt.pt --oss_repo /local/mnt/workspace/chenweng/executorch/EfficientSAM -v
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_esrgan --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --oss_repo /local/mnt/workspace/chenweng/executorch/Real-ESRGAN -v
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_eurobert --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --sentence_dataset /local/mnt/workspace/chenweng/executorch/wikisent2.txt
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_fastvit --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --image_dataset /local/mnt/workspace/chenweng/executorch/imagenet-mini/val --pretrained_weight /local/mnt/workspace/chenweng/executorch/fastvit_s12_reparam.pth.tar --oss_repo /local/mnt/workspace/chenweng/executorch/ml-fastvit -v
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_fbnet --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --image_dataset /local/mnt/workspace/chenweng/executorch/imagenet-mini/val
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_focalnet --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --image_dataset /local/mnt/workspace/chenweng/executorch/imagenet-mini/val
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_gMLP --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --image_dataset /local/mnt/workspace/chenweng/executorch/imagenet-mini/val
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_maxvit_t --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --image_dataset /local/mnt/workspace/chenweng/executorch/imagenet-mini/val
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_mobilevit_v1 --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --image_dataset /local/mnt/workspace/chenweng/executorch/imagenet-mini/val
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_mobilevit_v2 --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --image_dataset /local/mnt/workspace/chenweng/executorch/imagenet-mini/val
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_pvt --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --image_dataset /local/mnt/workspace/chenweng/executorch/imagenet-mini/val
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_regnet --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --image_dataset /local/mnt/workspace/chenweng/executorch/imagenet-mini/val
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_retinanet --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --image_dataset /local/mnt/workspace/chenweng/executorch/val2017
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_roberta --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --sentence_dataset /local/mnt/workspace/chenweng/executorch/wikisent2.txt
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_squeezenet --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --image_dataset /local/mnt/workspace/chenweng/executorch/imagenet-mini/val
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_ssd300_vgg16 --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --pretrained_weight /local/mnt/workspace/chenweng/executorch/checkpoint_ssd300.pth.tar --oss_repo /local/mnt/workspace/chenweng/executorch/a-PyTorch-Tutorial-to-Object-Detection
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_swin_transformer --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --image_dataset /local/mnt/workspace/chenweng/executorch/imagenet-mini/val
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_swin_v2_t --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --image_dataset /local/mnt/workspace/chenweng/executorch/imagenet-mini/val
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_t5 --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --qa_dataset /local/mnt/workspace/chenweng/executorch/SQuAD-v1.1.csv
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_vit_b_16 --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --image_dataset /local/mnt/workspace/chenweng/executorch/imagenet-mini/val
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleOssScript.test_whisper --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare

python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleScript.test_edsr --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --default_dataset
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleScript.test_inception_v3 --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --image_dataset /local/mnt/workspace/chenweng/executorch/imagenet-mini/val
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleScript.test_inception_v4 --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --image_dataset /local/mnt/workspace/chenweng/executorch/imagenet-mini/val
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleScript.test_mobilenet_v2 --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --image_dataset /local/mnt/workspace/chenweng/executorch/imagenet-mini/val
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleScript.test_mobilenet_v3 --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --image_dataset /local/mnt/workspace/chenweng/executorch/imagenet-mini/val
python ${EXECUTORCH_ROOT}/backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleScript.test_vit --model SM8650 --build_folder /local/mnt/workspace/chenweng/executorch/executorch/build-android --host <host> --device <device_id> --executorch_root ${EXECUTORCH_ROOT} --artifact_dir ./artifact_dir --backend gpu --online_prepare --image_dataset /local/mnt/workspace/chenweng/executorch/imagenet-mini/val

cc @cccclai @cbilgin

pytorch-bot · 2026-01-02T08:38:34Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16425

📄 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:

B200 runners are down due to network issues

✅ You can merge normally! (1 Unrelated Failure)

As of commit 2869a2b with merge base 47dc1de ():

UNSTABLE - The following job is marked as unstable, possibly due to flakiness on trunk:

pull / android / run-emulator (gh) (#16137)
Timeout waiting for emulator to boot.

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

github-actions · 2026-01-02T08:39:11Z

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.

cccclai · 2026-01-04T18:21:02Z

Thank you for the PR! Can you address the lint error

backends/qualcomm/quantizer/qconfig.py

cccclai · 2026-01-04T18:26:45Z

examples/qualcomm/oss_scripts/convnext_small.py

    instance = torchvision.models.convnext_small(weights="IMAGENET1K_V1").eval()
+    backend = get_backend_type(args.backend)
+    qnn_quantizer = {
+        QnnExecuTorchBackendType.kGpuBackend: None,


How do we expect user to use different backend for the quantizer part?

Actually, can you elaborate this part?

I am preparing next PR for llama on GPU, will update.

cccclai · 2026-01-04T18:28:30Z

Looks like some changes are in #16423..

meta-codesync · 2026-01-04T18:33:37Z

@cccclai has imported this pull request. If you are a Meta employee, you can view this in D90083741.

cccclai

Thank you! Do you have some estimated perf number?

chenweng-quic · 2026-01-07T07:02:20Z

Thank you! Do you have some estimated perf number?

I am preparing next PR for llama on GPU, will update perf number for these models.

chenweng-quic requested a review from cccclai as a code owner January 2, 2026 08:38

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 Jan 2, 2026

chenweng-quic added the module: qnn Issues related to Qualcomm's QNN delegate and code under backends/qualcomm/ label Jan 2, 2026

mergennachin requested a review from SS-JIA January 2, 2026 18:35

cccclai reviewed Jan 4, 2026

View reviewed changes

backends/qualcomm/quantizer/qconfig.py Outdated Show resolved Hide resolved

cccclai reviewed Jan 4, 2026

View reviewed changes

Qualcomm AI Engine Direct - Enable Example/OSS models on GPU backend

772f9dc

chenweng-quic force-pushed the enable_models_gpu branch from ea74436 to 772f9dc Compare January 5, 2026 05:41

chenweng-quic added 2 commits January 5, 2026 14:41

fix lint

8fa5da2

fix import error after lintrunner

2869a2b

chenweng-quic requested a review from cccclai January 7, 2026 03:06

cccclai approved these changes Jan 7, 2026

View reviewed changes

cccclai merged commit c5b05a9 into pytorch:main Jan 7, 2026
140 of 143 checks passed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Qualcomm AI Engine Direct - Enable Example/OSS models on GPU backend #16425

Qualcomm AI Engine Direct - Enable Example/OSS models on GPU backend #16425

Uh oh!

chenweng-quic commented Jan 2, 2026 •

edited by pytorch-bot bot

Loading

Uh oh!

pytorch-bot bot commented Jan 2, 2026 •

edited

Loading

Uh oh!

github-actions bot commented Jan 2, 2026

Uh oh!

cccclai commented Jan 4, 2026

Uh oh!

Uh oh!

cccclai Jan 4, 2026

Uh oh!

cccclai Jan 7, 2026

Uh oh!

chenweng-quic Jan 7, 2026

Uh oh!

cccclai commented Jan 4, 2026

Uh oh!

meta-codesync bot commented Jan 4, 2026

Uh oh!

cccclai left a comment

Uh oh!

Uh oh!

chenweng-quic commented Jan 7, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Qualcomm AI Engine Direct - Enable Example/OSS models on GPU backend #16425

Qualcomm AI Engine Direct - Enable Example/OSS models on GPU backend #16425

Uh oh!

Conversation

chenweng-quic commented Jan 2, 2026 • edited by pytorch-bot bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Succeed

Validation failed

Finalization failed

Has accuracy issue

Test plan

Uh oh!

pytorch-bot bot commented Jan 2, 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/16425

❗ 1 Active SEVs

✅ You can merge normally! (1 Unrelated Failure)

Uh oh!

github-actions bot commented Jan 2, 2026

This PR needs a release notes: label

Uh oh!

cccclai commented Jan 4, 2026

Uh oh!

Uh oh!

cccclai Jan 4, 2026

Choose a reason for hiding this comment

Uh oh!

cccclai Jan 7, 2026

Choose a reason for hiding this comment

Uh oh!

chenweng-quic Jan 7, 2026

Choose a reason for hiding this comment

Uh oh!

cccclai commented Jan 4, 2026

Uh oh!

meta-codesync bot commented Jan 4, 2026

Uh oh!

cccclai left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

chenweng-quic commented Jan 7, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

chenweng-quic commented Jan 2, 2026 •

edited by pytorch-bot bot

Loading

pytorch-bot bot commented Jan 2, 2026 •

edited

Loading

This PR needs a `release notes:` label