Skip to content
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.

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

Fixed a couple of dynamic shape detection issues #996

Closed

Conversation

chenyang78
Copy link
Contributor

Summary:
This diff fixed a couple of issues for dynamic shape detection:

  • handle cases where sample tensors may not have any dynamic dimension

  • added two lowering configs to guide dynamic shape detection

    (1) can_last_dim_be_dynamic: specifies if the last dimension can be dynamic
    (2) can_value_one_be_dynamic: specifies if dimension value one is allowed
    to appear at any dynamic dimension

Differential Revision: D54831007

@facebook-github-bot facebook-github-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 Mar 17, 2024
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D54831007

chenyang78 added a commit to chenyang78/AITemplate-fb-incubator that referenced this pull request Mar 17, 2024
Summary:

This diff fixed a couple of issues for dynamic shape detection:

* handle cases where sample tensors may not have any dynamic dimension

* added two lowering configs to guide dynamic shape detection

  (1) can_last_dim_be_dynamic: specifies if the last dimension can be dynamic
  (2) can_value_one_be_dynamic: specifies if dimension value one is allowed
      to appear at any dynamic dimension

Differential Revision: D54831007
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D54831007

chenyang78 added a commit to chenyang78/AITemplate-fb-incubator that referenced this pull request Mar 18, 2024
Summary:

This diff fixed a couple of issues for dynamic shape detection:

* handle cases where sample tensors may not have any dynamic dimension

* added two lowering configs to guide dynamic shape detection

  (1) can_last_dim_be_dynamic: specifies if the last dimension can be dynamic
  (2) can_value_one_be_dynamic: specifies if dimension value one is allowed
      to appear at any dynamic dimension

Differential Revision: D54831007
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D54831007

Summary:

This diff fixed a couple of issues for dynamic shape detection:

* handle cases where sample tensors may not have any dynamic dimension

* added two lowering configs to guide dynamic shape detection

  (1) can_last_dim_be_dynamic: specifies if the last dimension can be dynamic
  (2) can_value_one_be_dynamic: specifies if dimension value one is allowed
      to appear at any dynamic dimension

Differential Revision: D54831007
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D54831007

@facebook-github-bot
Copy link
Contributor

This pull request has been merged in d2dc957.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. fb-exported Merged
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants