KEMBAR78
Fix "expand: SymIntArrayRef expected to contain only concrete integers" in AOTInductor by ezyang · Pull Request #135933 · pytorch/pytorch · GitHub
Skip to content

Fix "expand: SymIntArrayRef expected to contain only concrete integers" in AOTInductor #135933

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Closed
wants to merge 1 commit into from
Closed

Fix "expand: SymIntArrayRef expected to contain only concrete integers" in AOTInductor #135933

wants to merge 1 commit into from

Conversation

@ezyang
Copy link
Contributor

@ezyang ezyang commented Sep 13, 2024 •
edited by pytorch-bot bot
Loading

@ezyang
Update
b33d98d 
[ghstack-poisoned]
@pytorch-bot
Copy link

pytorch-bot bot commented Sep 13, 2024 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/135933

Note: Links to docs will display an error until the docs builds have been completed.

✅ No Failures

As of commit b33d98d with merge base failed to retrieve merge base, please contact dev infra:
💚 Looks good so far! There are no failures yet. 💚

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

ezyang added a commit that referenced this pull request Sep 13, 2024
@ezyang
Fix "expand: SymIntArrayRef expected to contain only concrete integer…
315e698 
…s" in AOTInductor

Internal xref:
https://fb.workplace.com/groups/1075192433118967/permalink/1501860707118802/

Signed-off-by: Edward Z. Yang <ezyang@meta.com>

ghstack-source-id: 46fee3b
Pull Request resolved: #135933
@ezyang
Copy link
Contributor Author

ezyang commented Sep 13, 2024

@pytorchbot merge

@pytorch-bot pytorch-bot bot added the ciflow/trunk Trigger trunk jobs on your pull request label Sep 13, 2024
@pytorchmergebot
Copy link
Collaborator

Merge started

Your change will be merged once all checks pass (ETA 0-4 Hours).

Learn more about merging in the wiki.

Questions? Feedback? Please reach out to the PyTorch DevX Team

Advanced Debugging
Check the merge workflow status
here

@lucylq lucylq mentioned this pull request Sep 13, 2024
Closed
facebook-github-bot pushed a commit to pytorch/executorch that referenced this pull request Sep 13, 2024
@lucylq @facebook-github-bot
Register preprocess in pytorch (#5350)
994aec9 
Summary:
- Following https://pytorch.org/executorch/stable/kernel-library-custom-aten-kernel.html, use WRAP_TO_ATEN to register preprocess in pytorch
- Create a separate `op_tile_crop_aot.py` that registers the C++ aot library into Python. Inside export_preprocess, use `op_tile_crop_aot.py` instead of `preprocess_custom_ops.py`, which is the pure python lib. Otherwise, we end up loading the C++ library when the python one already exists.



Note, include these PyTorch changes for AOTI export:
pytorch/pytorch#135933


Test Plan:
```
>>> import torch
>>> from executorch.extension.llm.custom_ops import sdpa_with_kv_cache  # noqa # usort: skip
>>> x = torch._export.aot_load("/home/lfq/local/executorch/aoti_preprocess.so", "cpu")
>>> img = torch.ones([3, 600, 800])
>>> canvas_size = torch.tensor([448, 448])
>>> target_size = torch.tensor([336, 448])
>>> res = x(img, target_size, canvas_size)
>>> res[0].shape
torch.Size([4, 3, 224, 224])
>>> res[1]
tensor([2, 2])
>>>
```

Reviewed By: larryliu0820

Differential Revision: D62651605

Pulled By: lucylq
facebook-github-bot pushed a commit to pytorch/executorch that referenced this pull request Sep 13, 2024
@lucylq @facebook-github-bot
Register preprocess in pytorch (#5350)
bc65c1d 
Summary:
- Following https://pytorch.org/executorch/stable/kernel-library-custom-aten-kernel.html, use WRAP_TO_ATEN to register preprocess in pytorch
- Create a separate `op_tile_crop_aot.py` that registers the C++ aot library into Python. Inside export_preprocess, use `op_tile_crop_aot.py` instead of `preprocess_custom_ops.py`, which is the pure python lib. Otherwise, we end up loading the C++ library when the python one already exists.



Note, include these PyTorch changes for AOTI export:
pytorch/pytorch#135933


Test Plan:
```
>>> import torch
>>> from executorch.extension.llm.custom_ops import sdpa_with_kv_cache  # noqa # usort: skip
>>> x = torch._export.aot_load("/home/lfq/local/executorch/aoti_preprocess.so", "cpu")
>>> img = torch.ones([3, 600, 800])
>>> canvas_size = torch.tensor([448, 448])
>>> target_size = torch.tensor([336, 448])
>>> res = x(img, target_size, canvas_size)
>>> res[0].shape
torch.Size([4, 3, 224, 224])
>>> res[1]
tensor([2, 2])
>>>
```

Reviewed By: larryliu0820

Differential Revision: D62651605

Pulled By: lucylq
facebook-github-bot pushed a commit to pytorch/executorch that referenced this pull request Sep 13, 2024
@lucylq @facebook-github-bot
Register preprocess in pytorch (#5350)
9721e98 
Summary:
- Following https://pytorch.org/executorch/stable/kernel-library-custom-aten-kernel.html, use WRAP_TO_ATEN to register preprocess in pytorch
- Create a separate `op_tile_crop_aot.py` that registers the C++ aot library into Python. Inside export_preprocess, use `op_tile_crop_aot.py` instead of `preprocess_custom_ops.py`, which is the pure python lib. Otherwise, we end up loading the C++ library when the python one already exists.



Note, include these PyTorch changes for AOTI export:
pytorch/pytorch#135933


Test Plan:
```
>>> import torch
>>> from executorch.extension.llm.custom_ops import sdpa_with_kv_cache  # noqa # usort: skip
>>> x = torch._export.aot_load("/home/lfq/local/executorch/aoti_preprocess.so", "cpu")
>>> img = torch.ones([3, 600, 800])
>>> canvas_size = torch.tensor([448, 448])
>>> target_size = torch.tensor([336, 448])
>>> res = x(img, target_size, canvas_size)
>>> res[0].shape
torch.Size([4, 3, 224, 224])
>>> res[1]
tensor([2, 2])
>>>
```

Reviewed By: larryliu0820

Differential Revision: D62651605

Pulled By: lucylq
facebook-github-bot pushed a commit to pytorch/executorch that referenced this pull request Sep 13, 2024
@lucylq @facebook-github-bot
Register preprocess in pytorch (#5350)
cfe1be1 
Summary:
- Following https://pytorch.org/executorch/stable/kernel-library-custom-aten-kernel.html, use WRAP_TO_ATEN to register preprocess in pytorch
- Create a separate `op_tile_crop_aot.py` that registers the C++ aot library into Python. Inside export_preprocess, use `op_tile_crop_aot.py` instead of `preprocess_custom_ops.py`, which is the pure python lib. Otherwise, we end up loading the C++ library when the python one already exists.



Note, include these PyTorch changes for AOTI export:
pytorch/pytorch#135933


Test Plan:
```
>>> import torch
>>> from executorch.extension.llm.custom_ops import sdpa_with_kv_cache  # noqa # usort: skip
>>> x = torch._export.aot_load("/home/lfq/local/executorch/aoti_preprocess.so", "cpu")
>>> img = torch.ones([3, 600, 800])
>>> canvas_size = torch.tensor([448, 448])
>>> target_size = torch.tensor([336, 448])
>>> res = x(img, target_size, canvas_size)
>>> res[0].shape
torch.Size([4, 3, 224, 224])
>>> res[1]
tensor([2, 2])
>>>
```

Reviewed By: larryliu0820

Differential Revision: D62651605

Pulled By: lucylq
facebook-github-bot pushed a commit to pytorch/executorch that referenced this pull request Sep 16, 2024
@lucylq @facebook-github-bot
Register preprocess in pytorch (#5350)
28cda3a 
Summary:
- Following https://pytorch.org/executorch/stable/kernel-library-custom-aten-kernel.html, use WRAP_TO_ATEN to register preprocess in pytorch
- Create a separate `op_tile_crop_aot.py` that registers the C++ aot library into Python. Inside export_preprocess, use `op_tile_crop_aot.py` instead of `preprocess_custom_ops.py`, which is the pure python lib. Otherwise, we end up loading the C++ library when the python one already exists.



Note, include these PyTorch changes for AOTI export:
pytorch/pytorch#135933


Test Plan:
```
>>> import torch
>>> from executorch.extension.llm.custom_ops import sdpa_with_kv_cache  # noqa # usort: skip
>>> x = torch._export.aot_load("/home/lfq/local/executorch/aoti_preprocess.so", "cpu")
>>> img = torch.ones([3, 600, 800])
>>> canvas_size = torch.tensor([448, 448])
>>> target_size = torch.tensor([336, 448])
>>> res = x(img, target_size, canvas_size)
>>> res[0].shape
torch.Size([4, 3, 224, 224])
>>> res[1]
tensor([2, 2])
>>>
```

Reviewed By: larryliu0820

Differential Revision: D62651605

Pulled By: lucylq
lucylq added a commit to pytorch/executorch that referenced this pull request Sep 16, 2024
@lucylq @facebook-github-bot
Register preprocess in pytorch (#5350)
1c56da0 
Summary:
- Following https://pytorch.org/executorch/stable/kernel-library-custom-aten-kernel.html, use WRAP_TO_ATEN to register preprocess in pytorch
- Create a separate `op_tile_crop_aot.py` that registers the C++ aot library into Python. Inside export_preprocess, use `op_tile_crop_aot.py` instead of `preprocess_custom_ops.py`, which is the pure python lib. Otherwise, we end up loading the C++ library when the python one already exists.

Note, include these PyTorch changes for AOTI export:
pytorch/pytorch#135933

Pull Request resolved: #5350

Test Plan:
```
>>> import torch
>>> from executorch.extension.llm.custom_ops import sdpa_with_kv_cache  # noqa # usort: skip
>>> x = torch._export.aot_load("/home/lfq/local/executorch/aoti_preprocess.so", "cpu")
>>> img = torch.ones([3, 600, 800])
>>> canvas_size = torch.tensor([448, 448])
>>> target_size = torch.tensor([336, 448])
>>> res = x(img, target_size, canvas_size)
>>> res[0].shape
torch.Size([4, 3, 224, 224])
>>> res[1]
tensor([2, 2])
>>>
```

Differential Revision: D62651605

Reviewed By: larryliu0820

Pulled By: lucylq
facebook-github-bot pushed a commit to pytorch/executorch that referenced this pull request Sep 16, 2024
@lucylq @facebook-github-bot
Register preprocess in pytorch (#5350)
e24287b 
Summary:
- Following https://pytorch.org/executorch/stable/kernel-library-custom-aten-kernel.html, use WRAP_TO_ATEN to register preprocess in pytorch
- Create a separate `op_tile_crop_aot.py` that registers the C++ aot library into Python. Inside export_preprocess, use `op_tile_crop_aot.py` instead of `preprocess_custom_ops.py`, which is the pure python lib. Otherwise, we end up loading the C++ library when the python one already exists.



Note, include these PyTorch changes for AOTI export:
pytorch/pytorch#135933


Test Plan:
```
>>> import torch
>>> from executorch.extension.llm.custom_ops import sdpa_with_kv_cache  # noqa # usort: skip
>>> x = torch._export.aot_load("/home/lfq/local/executorch/aoti_preprocess.so", "cpu")
>>> img = torch.ones([3, 600, 800])
>>> canvas_size = torch.tensor([448, 448])
>>> target_size = torch.tensor([336, 448])
>>> res = x(img, target_size, canvas_size)
>>> res[0].shape
torch.Size([4, 3, 224, 224])
>>> res[1]
tensor([2, 2])
>>>
```

Reviewed By: larryliu0820

Differential Revision: D62651605

Pulled By: lucylq
lucylq added a commit to pytorch/executorch that referenced this pull request Sep 16, 2024
@lucylq @facebook-github-bot
Register preprocess in pytorch (#5350)
4d4cbfd 
Summary:
- Following https://pytorch.org/executorch/stable/kernel-library-custom-aten-kernel.html, use WRAP_TO_ATEN to register preprocess in pytorch
- Create a separate `op_tile_crop_aot.py` that registers the C++ aot library into Python. Inside export_preprocess, use `op_tile_crop_aot.py` instead of `preprocess_custom_ops.py`, which is the pure python lib. Otherwise, we end up loading the C++ library when the python one already exists.

Note, include these PyTorch changes for AOTI export:
pytorch/pytorch#135933

Pull Request resolved: #5350

Test Plan:
```
>>> import torch
>>> from executorch.extension.llm.custom_ops import sdpa_with_kv_cache  # noqa # usort: skip
>>> x = torch._export.aot_load("/home/lfq/local/executorch/aoti_preprocess.so", "cpu")
>>> img = torch.ones([3, 600, 800])
>>> canvas_size = torch.tensor([448, 448])
>>> target_size = torch.tensor([336, 448])
>>> res = x(img, target_size, canvas_size)
>>> res[0].shape
torch.Size([4, 3, 224, 224])
>>> res[1]
tensor([2, 2])
>>>
```

Reviewed By: larryliu0820

Differential Revision: D62651605

Pulled By: lucylq
facebook-github-bot pushed a commit to pytorch/executorch that referenced this pull request Sep 16, 2024
@lucylq @facebook-github-bot
Register preprocess in pytorch (#5350)
59b8170 
Summary:
- Following https://pytorch.org/executorch/stable/kernel-library-custom-aten-kernel.html, use WRAP_TO_ATEN to register preprocess in pytorch
- Create a separate `op_tile_crop_aot.py` that registers the C++ aot library into Python. Inside export_preprocess, use `op_tile_crop_aot.py` instead of `preprocess_custom_ops.py`, which is the pure python lib. Otherwise, we end up loading the C++ library when the python one already exists.



Note, include these PyTorch changes for AOTI export:
pytorch/pytorch#135933


Test Plan:
```
>>> import torch
>>> from executorch.extension.llm.custom_ops import sdpa_with_kv_cache  # noqa # usort: skip
>>> x = torch._export.aot_load("/home/lfq/local/executorch/aoti_preprocess.so", "cpu")
>>> img = torch.ones([3, 600, 800])
>>> canvas_size = torch.tensor([448, 448])
>>> target_size = torch.tensor([336, 448])
>>> res = x(img, target_size, canvas_size)
>>> res[0].shape
torch.Size([4, 3, 224, 224])
>>> res[1]
tensor([2, 2])
>>>
```

Reviewed By: larryliu0820

Differential Revision: D62651605

Pulled By: lucylq
facebook-github-bot pushed a commit to pytorch/executorch that referenced this pull request Sep 16, 2024
@lucylq @facebook-github-bot
Register preprocess in pytorch (#5350)
8a8e876 
Summary:
- Following https://pytorch.org/executorch/stable/kernel-library-custom-aten-kernel.html, use WRAP_TO_ATEN to register preprocess in pytorch
- Create a separate `op_tile_crop_aot.py` that registers the C++ aot library into Python. Inside export_preprocess, use `op_tile_crop_aot.py` instead of `preprocess_custom_ops.py`, which is the pure python lib. Otherwise, we end up loading the C++ library when the python one already exists.

Note, include these PyTorch changes for AOTI export:
pytorch/pytorch#135933

Pull Request resolved: #5350

Test Plan:
```
>>> import torch
>>> from executorch.extension.llm.custom_ops import sdpa_with_kv_cache  # noqa # usort: skip
>>> x = torch._export.aot_load("/home/lfq/local/executorch/aoti_preprocess.so", "cpu")
>>> img = torch.ones([3, 600, 800])
>>> canvas_size = torch.tensor([448, 448])
>>> target_size = torch.tensor([336, 448])
>>> res = x(img, target_size, canvas_size)
>>> res[0].shape
torch.Size([4, 3, 224, 224])
>>> res[1]
tensor([2, 2])
>>>
```

Reviewed By: larryliu0820

Differential Revision: D62651605

Pulled By: lucylq

fbshipit-source-id: bdf5b46033ebbd73d10307ab58219743a73fd6fd
lucylq added a commit to pytorch/executorch that referenced this pull request Sep 17, 2024
@lucylq
Register preprocess in pytorch (#5350)
486b70a 
Summary:
- Following https://pytorch.org/executorch/stable/kernel-library-custom-aten-kernel.html, use WRAP_TO_ATEN to register preprocess in pytorch
- Create a separate `op_tile_crop_aot.py` that registers the C++ aot library into Python. Inside export_preprocess, use `op_tile_crop_aot.py` instead of `preprocess_custom_ops.py`, which is the pure python lib. Otherwise, we end up loading the C++ library when the python one already exists.

Note, include these PyTorch changes for AOTI export:
pytorch/pytorch#135933

Pull Request resolved: #5350

Test Plan:
```
>>> import torch
>>> from executorch.extension.llm.custom_ops import sdpa_with_kv_cache  # noqa # usort: skip
>>> x = torch._export.aot_load("/home/lfq/local/executorch/aoti_preprocess.so", "cpu")
>>> img = torch.ones([3, 600, 800])
>>> canvas_size = torch.tensor([448, 448])
>>> target_size = torch.tensor([336, 448])
>>> res = x(img, target_size, canvas_size)
>>> res[0].shape
torch.Size([4, 3, 224, 224])
>>> res[1]
tensor([2, 2])
>>>
```

Reviewed By: larryliu0820

Differential Revision: D62651605

Pulled By: lucylq

fbshipit-source-id: bdf5b46033ebbd73d10307ab58219743a73fd6fd
Chao1Han pushed a commit to Chao1Han/pytorch that referenced this pull request Sep 20, 2024
@ezyang @Chao1Han
Fix "expand: SymIntArrayRef expected to contain only concrete integer…
1a96117 
…s" in AOTInductor (pytorch#135933)

Internal xref:
https://fb.workplace.com/groups/1075192433118967/permalink/1501860707118802/

Signed-off-by: Edward Z. Yang <ezyang@meta.com>

Pull Request resolved: pytorch#135933
Approved by: https://github.com/angelayi
@github-actions github-actions bot deleted the gh/ezyang/2930/head branch October 14, 2024 06:24
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@angelayi angelayi angelayi approved these changes

@albanD albanD Awaiting requested review from albanD

@antoniojkim antoniojkim Awaiting requested review from antoniojkim

@bdhirsh bdhirsh Awaiting requested review from bdhirsh

@miladm miladm Awaiting requested review from miladm

@SherlockNoMad SherlockNoMad Awaiting requested review from SherlockNoMad

Assignees

No one assigned

Labels

ciflow/inductor ciflow/trunk Trigger trunk jobs on your pull request Merged module: inductor release notes: inductor topic: bug fixes topic category

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@ezyang @pytorchmergebot @angelayi