Skip to content

Conversation

PaulZhang12
Copy link
Contributor

Previously, the TorchRec inference solution used torch.deploy, which isn't supported, and the solution itself was outdated and broken. This PR revamps the inference example with Torch.FX and TorchScript, which more accurately represents what is used in production for RecSys currently. Furthermore, the example was constructed with simplicity as the top priority, with fewer package requirements and steps to run. This is the first iteration of the inference example, with more to come!

@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 Jun 12, 2024
@facebook-github-bot
Copy link
Contributor

@PaulZhang12 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

PaulZhang12 added a commit that referenced this pull request Jun 12, 2024
…olution (#2101)

Summary:
Previously, the TorchRec inference solution used torch.deploy, which isn't supported, and the solution itself was outdated and broken. This PR revamps the inference example with Torch.FX and TorchScript, which more accurately represents what is used in production for RecSys currently. Furthermore, the example was constructed with simplicity as the top priority, with fewer package requirements and steps to run. This is the first iteration of the inference example, with more to come!

Pull Request resolved: #2101

Differential Revision: D58478461

Pulled By: PaulZhang12
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D58478461

PaulZhang12 added a commit that referenced this pull request Jun 13, 2024
…olution (#2101)

Summary:
Previously, the TorchRec inference solution used torch.deploy, which isn't supported, and the solution itself was outdated and broken. This PR revamps the inference example with Torch.FX and TorchScript, which more accurately represents what is used in production for RecSys currently. Furthermore, the example was constructed with simplicity as the top priority, with fewer package requirements and steps to run. This is the first iteration of the inference example, with more to come!

Pull Request resolved: #2101

Differential Revision: D58478461

Pulled By: PaulZhang12
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D58478461

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

This pull request was exported from Phabricator. Differential Revision: D58478461

PaulZhang12 added a commit that referenced this pull request Jun 14, 2024
…olution (#2101)

Summary:
Previously, the TorchRec inference solution used torch.deploy, which isn't supported, and the solution itself was outdated and broken. This PR revamps the inference example with Torch.FX and TorchScript, which more accurately represents what is used in production for RecSys currently. Furthermore, the example was constructed with simplicity as the top priority, with fewer package requirements and steps to run. This is the first iteration of the inference example, with more to come!

Pull Request resolved: #2101

Differential Revision: D58478461

Pulled By: PaulZhang12
…olution (#2101)

Summary:
Previously, the TorchRec inference solution used torch.deploy, which isn't supported, and the solution itself was outdated and broken. This PR revamps the inference example with Torch.FX and TorchScript, which more accurately represents what is used in production for RecSys currently. Furthermore, the example was constructed with simplicity as the top priority, with fewer package requirements and steps to run. This is the first iteration of the inference example, with more to come!

Pull Request resolved: #2101

Differential Revision: D58478461

Pulled By: PaulZhang12
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D58478461

@TroyGarden TroyGarden deleted the inference-fix branch June 4, 2025 05:59
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
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants