Add methods to detach model from sparse data dist staged pipeline #2049
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D57688338 |
sarckk
added a commit
to sarckk/torchrec
that referenced
this pull request
May 28, 2024
…torch#2049) Summary: Sparse data dist pipelining causes sharded trec module forward to be replaced with `PipelinedForward` variants that uses context to fetch data for current rank. However, there are use cases where we want to perform a simple forward on the trec sharded modules without using a pipeline (e.g. for simple local debug evals during training). In such cases, it is useful to have a way to detach and re-attach the model from SDD pipelining. Reviewed By: zzzwen Differential Revision: D57688338
|
This pull request was exported from Phabricator. Differential Revision: D57688338 |
…torch#2049) Summary: Sparse data dist pipelining causes sharded trec module forward to be replaced with `PipelinedForward` variants that uses context to fetch data for current rank. However, there are use cases where we want to perform a simple forward on the trec sharded modules without using a pipeline (e.g. for simple local debug evals during training). In such cases, it is useful to have a way to detach and re-attach the model from SDD pipelining. Reviewed By: zzzwen Differential Revision: D57688338
|
This pull request was exported from Phabricator. Differential Revision: D57688338 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary: Sparse data dist pipelining causes sharded trec module forward to be replaced with
PipelinedForwardvariants that uses context to fetch data for current rank. However, there are use cases where we want to perform a simple forward on the trec sharded modules without using a pipeline (e.g. for simple local debug evals during training). In such cases, it is useful to have a way to detach and re-attach the model from SDD pipelining.Reviewed By: zzzwen
Differential Revision: D57688338