KEMBAR78
[AOTInductor] ProxyExecutor supports Tuple of Tensor and List[Tensor] in returns by SherlockNoMad · Pull Request #110187 · pytorch/pytorch · GitHub
Skip to content

[AOTInductor] ProxyExecutor supports Tuple of Tensor and List[Tensor] in returns #110187

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

[AOTInductor] ProxyExecutor supports Tuple of Tensor and List[Tensor] in returns #110187

wants to merge 1 commit into from

Conversation

@SherlockNoMad
Copy link
Contributor

@SherlockNoMad SherlockNoMad commented Sep 27, 2023 •
edited by pytorch-bot bot
Loading

Summary:
ProxyExecutor supports custom ops that return a tuple mixed of Tensor and List[Tensor]
e.g. "fn_with_mix_outputs(Tensor t, Tensor[] tensors) -> (Tensor, Tensor[])"

Example:
out7, [out8, out9] = torch.ops.fb.fn_with_mix_outputs(out5, [out6, out4])
got compiled into

    AtenTensorHandle buf11_handle;  // output buffer
    AOTI_TORCH_ERROR_CODE_CHECK(aoti_torch_new_uninitialized_tensor(&buf11_handle));
    RAIIAtenTensorHandle buf11(buf11_handle);
    AtenTensorHandle buf12_handle;  // output buffer
    AOTI_TORCH_ERROR_CODE_CHECK(aoti_torch_new_uninitialized_tensor(&buf12_handle));
    RAIIAtenTensorHandle buf12(buf12_handle);
    AtenTensorHandle buf13_handle;  // output buffer
    AOTI_TORCH_ERROR_CODE_CHECK(aoti_torch_new_uninitialized_tensor(&buf13_handle));
    RAIIAtenTensorHandle buf13(buf13_handle);
    AtenTensorHandle tensor_args_var_7[] = {buf8.get(), buf9.get(), buf6.get(), buf11.get(), buf12.get(), buf13.get()};
    int64_t int_args_var_8[] = {};
    aoti_torch_proxy_executor_call_function(proxy_executor, 3, 0, int_args_var_8, 6, tensor_args_var_7);

Serialized extern node

    {
      "name": "buf10",
      "node": {
        "target": "fb::fn_with_mix_outputs",
        "inputs": [
          {
            "name": "t",
            "arg": {
              "asTensor": {
                "name": "buf8"
              }
            }
          },
          {
            "name": "tensors",
            "arg": {
              "asTensors": [
                {
                  "name": "buf9"
                },
                {
                  "name": "buf6"
                }
              ]
            }
          }
        ],
        "outputs": [
          {
            "asTensor": {
              "name": "buf11"
            }
          },
          {
            "asTensors": [
              {
                "name": "buf12"
              },
              {
                "name": "buf13"
              }
            ]
          }
        ],
        "metadata": {}
      }
    }

Test Plan: Test

Differential Revision: D49710320

cc @voznesenskym @penguinwu @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @Xia-Weiwen @wenzhe-nrv @jiayisunx @peterbell10 @ipiszy @yf225 @chenyang78 @kadeng @muchulee8 @aakhundov @ColinPeppler

@pytorch-bot
Copy link

pytorch-bot bot commented Sep 27, 2023 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/110187

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

✅ You can merge normally! (2 Unrelated Failures)

As of commit 0d4fe24 with merge base bc047ec (image):

BROKEN TRUNK - The following jobs failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

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

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D49710320

@SherlockNoMad SherlockNoMad added the topic: not user facing topic category label Sep 28, 2023
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D49710320

SherlockNoMad added a commit to SherlockNoMad/pytorch that referenced this pull request Sep 28, 2023
@SherlockNoMad @facebook-github-bot
[AOTInductor] ProxyExecutor supports Tuple of Tensor and List[Tensor]…
d6784c4 
… in returns (pytorch#110187)

Summary:
Pull Request resolved: pytorch#110187

ProxyExecutor supports custom ops that return a tuple mixed of Tensor and List[Tensor]
e.g. `"fn_with_mix_outputs(Tensor t, Tensor[] tensors) -> (Tensor, Tensor[])"`

Example:
`out7, [out8, out9] = torch.ops.fb.fn_with_mix_outputs(out5, [out6, out4])`
got compiled into
```
    AtenTensorHandle buf11_handle;  // output buffer
    AOTI_TORCH_ERROR_CODE_CHECK(aoti_torch_new_uninitialized_tensor(&buf11_handle));
    RAIIAtenTensorHandle buf11(buf11_handle);
    AtenTensorHandle buf12_handle;  // output buffer
    AOTI_TORCH_ERROR_CODE_CHECK(aoti_torch_new_uninitialized_tensor(&buf12_handle));
    RAIIAtenTensorHandle buf12(buf12_handle);
    AtenTensorHandle buf13_handle;  // output buffer
    AOTI_TORCH_ERROR_CODE_CHECK(aoti_torch_new_uninitialized_tensor(&buf13_handle));
    RAIIAtenTensorHandle buf13(buf13_handle);
    AtenTensorHandle tensor_args_var_7[] = {buf8.get(), buf9.get(), buf6.get(), buf11.get(), buf12.get(), buf13.get()};
    int64_t int_args_var_8[] = {};
    aoti_torch_proxy_executor_call_function(proxy_executor, 3, 0, int_args_var_8, 6, tensor_args_var_7);
```

Serialized extern node
```
    {
      "name": "buf10",
      "node": {
        "target": "fb::fn_with_mix_outputs",
        "inputs": [
          {
            "name": "t",
            "arg": {
              "asTensor": {
                "name": "buf8"
              }
            }
          },
          {
            "name": "tensors",
            "arg": {
              "asTensors": [
                {
                  "name": "buf9"
                },
                {
                  "name": "buf6"
                }
              ]
            }
          }
        ],
        "outputs": [
          {
            "asTensor": {
              "name": "buf11"
            }
          },
          {
            "asTensors": [
              {
                "name": "buf12"
              },
              {
                "name": "buf13"
              }
            ]
          }
        ],
        "metadata": {}
      }
    }
```

Test Plan: Test

Differential Revision: D49710320

fbshipit-source-id: f4403608c5021f9e1f88926f59338578b844147f
@SherlockNoMad SherlockNoMad mentioned this pull request Sep 28, 2023
Closed
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D49710320

1 similar comment
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D49710320

@SherlockNoMad @facebook-github-bot
[AOTInductor] ProxyExecutor supports Tuple of Tensor and List[Tensor]…
0d4fe24 
… in returns (pytorch#110187)

Summary:

ProxyExecutor supports custom ops that return a tuple mixed of Tensor and List[Tensor]
e.g. `"fn_with_mix_outputs(Tensor t, Tensor[] tensors) -> (Tensor, Tensor[])"`


Example:
`out7, [out8, out9] = torch.ops.fb.fn_with_mix_outputs(out5, [out6, out4])`
got compiled into
```
    AtenTensorHandle buf11_handle;  // output buffer
    AOTI_TORCH_ERROR_CODE_CHECK(aoti_torch_new_uninitialized_tensor(&buf11_handle));
    RAIIAtenTensorHandle buf11(buf11_handle);
    AtenTensorHandle buf12_handle;  // output buffer
    AOTI_TORCH_ERROR_CODE_CHECK(aoti_torch_new_uninitialized_tensor(&buf12_handle));
    RAIIAtenTensorHandle buf12(buf12_handle);
    AtenTensorHandle buf13_handle;  // output buffer
    AOTI_TORCH_ERROR_CODE_CHECK(aoti_torch_new_uninitialized_tensor(&buf13_handle));
    RAIIAtenTensorHandle buf13(buf13_handle);
    AtenTensorHandle tensor_args_var_7[] = {buf8.get(), buf9.get(), buf6.get(), buf11.get(), buf12.get(), buf13.get()};
    int64_t int_args_var_8[] = {};
    aoti_torch_proxy_executor_call_function(proxy_executor, 3, 0, int_args_var_8, 6, tensor_args_var_7);
```

Serialized extern node
```
    {
      "name": "buf10",
      "node": {
        "target": "fb::fn_with_mix_outputs",
        "inputs": [
          {
            "name": "t",
            "arg": {
              "asTensor": {
                "name": "buf8"
              }
            }
          },
          {
            "name": "tensors",
            "arg": {
              "asTensors": [
                {
                  "name": "buf9"
                },
                {
                  "name": "buf6"
                }
              ]
            }
          }
        ],
        "outputs": [
          {
            "asTensor": {
              "name": "buf11"
            }
          },
          {
            "asTensors": [
              {
                "name": "buf12"
              },
              {
                "name": "buf13"
              }
            ]
          }
        ],
        "metadata": {}
      }
    }
```

Test Plan: Test

Differential Revision: D49710320
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D49710320

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D49710320

chenyang78
chenyang78 approved these changes Sep 29, 2023
View reviewed changes
Copy link
Contributor

@chenyang78 chenyang78 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM. Thanks.

@facebook-github-bot
Copy link
Contributor

@pytorchbot merge

(Initiating merge automatically since Phabricator Diff has merged)

@pytorch-bot pytorch-bot bot added the ciflow/trunk Trigger trunk jobs on your pull request label Sep 30, 2023
@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

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@chenyang78 chenyang78 chenyang78 approved these changes

@desertfire desertfire Awaiting requested review from desertfire

Assignees

No one assigned

Labels

ciflow/inductor ciflow/trunk Trigger trunk jobs on your pull request fb-exported Merged module: inductor topic: not user facing topic category

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@SherlockNoMad @facebook-github-bot @pytorchmergebot @chenyang78