Delete copy of quantized SDPA in torchao/experimental #13924
Conversation
metascroy
requested review from
jackzhxng,
larryliu0820,
mergennachin and
swolchok
as code owners
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/13924
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit b87901a with merge base 79744f0 ( 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
|
This pull request was exported from Phabricator. Differential Revision: D81640227 |
This PR needs a
|
kimishpatel
left a comment
kimishpatel
left a comment
There was a problem hiding this comment.
Review automatically exported from Phabricator review in Meta.
|
@metascroy has imported this pull request. If you are a Meta employee, you can view this in D81640227. |
|
@metascroy has imported this pull request. If you are a Meta employee, you can view this in D81640227. |
|
@metascroy has imported this pull request. If you are a Meta employee, you can view this in D81640227. |
|
@metascroy has imported this pull request. If you are a Meta employee, you can view this in D81640227. |
1 similar comment
|
@metascroy has imported this pull request. If you are a Meta employee, you can view this in D81640227. |
|
@metascroy has imported this pull request. If you are a Meta employee, you can view this in D81640227. |
2 similar comments
|
@metascroy has imported this pull request. If you are a Meta employee, you can view this in D81640227. |
|
@metascroy has imported this pull request. If you are a Meta employee, you can view this in D81640227. |
Summary: This deletes the SDPA/matmul kernels in torchao/experimental. These kernels were already migrated to torchao/csrc/cpu/torch_free_kernels in the first diff, but we needed to keep them around in torchao/experimental to do a pin bump in ExecuTorch OSS after the first diff lands. X-link: pytorch/executorch#13924 Reviewed By: kimishpatel Differential Revision: D81640227 Pulled By: metascroy
metascroy
force-pushed
the
export-D81640227
branch
from
6963687 to
d661eba
Compare
Summary: X-link: pytorch/ao#2952 This deletes the SDPA/matmul kernels in torchao/experimental. These kernels were already migrated to torchao/csrc/cpu/torch_free_kernels in the first diff, but we needed to keep them around in torchao/experimental to do a pin bump in ExecuTorch OSS after the first diff lands. Test Plan: Imported from GitHub, without a `Test Plan:` line. Rollback Plan: Reviewed By: kimishpatel Differential Revision: D81640227 Pulled By: metascroy
|
This pull request was exported from Phabricator. Differential Revision: D81640227 |
Summary: This deletes the SDPA/matmul kernels in torchao/experimental. These kernels were already migrated to torchao/csrc/cpu/torch_free_kernels in the first diff, but we needed to keep them around in torchao/experimental to do a pin bump in ExecuTorch OSS after the first diff lands. X-link: pytorch/executorch#13924 Test Plan: Imported from GitHub, without a `Test Plan:` line. Rollback Plan: Reviewed By: kimishpatel Differential Revision: D81640227 Pulled By: metascroy
Summary: Pull Request resolved: pytorch#2952 This deletes the SDPA/matmul kernels in torchao/experimental. These kernels were already migrated to torchao/csrc/cpu/torch_free_kernels in the first diff, but we needed to keep them around in torchao/experimental to do a pin bump in ExecuTorch OSS after the first diff lands. X-link: pytorch/executorch#13924 Test Plan: Imported from GitHub, without a `Test Plan:` line. Rollback Plan: Reviewed By: kimishpatel Differential Revision: D81640227 Pulled By: metascroy
Summary: X-link: pytorch/ao#2952 This deletes the SDPA/matmul kernels in torchao/experimental. These kernels were already migrated to torchao/csrc/cpu/torch_free_kernels in the first diff, but we needed to keep them around in torchao/experimental to do a pin bump in ExecuTorch OSS after the first diff lands. Pull Request resolved: pytorch#13924 Test Plan: Imported from GitHub, without a `Test Plan:` line. Rollback Plan: Reviewed By: kimishpatel Differential Revision: D81640227 Pulled By: metascroy
|
This pull request was exported from Phabricator. Differential Revision: D81640227 |
metascroy
force-pushed
the
export-D81640227
branch
from
d661eba to
b87901a
Compare
3 participants
Summary:
This deletes the SDPA/matmul kernels in torchao/experimental.
These kernels were already migrated to torchao/csrc/cpu/torch_free_kernels in the first diff, but we needed to keep them around in torchao/experimental to do a pin bump in ExecuTorch OSS after the first diff lands.
Differential Revision: D81640227