Support skipping offsets computation in KJT to_dict #3503
Closed
Conversation
This file contains hidden or 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
meta-cla
bot
added
the
CLA Signed
coufon
added a commit
to coufon/torchrec
that referenced
this pull request
Nov 1, 2025
Summary: This diff optimizes KeyedJaggedTensor.to_dict by optionally removing several unnecessary offset computation. It can evidently improve latency if offsets are not needed in the outputs. Differential Revision: D85995629
coufon
force-pushed
the
export-D85995629
branch
from
5f64850 to
d2347fc
Compare
coufon
added a commit
to coufon/torchrec
that referenced
this pull request
Nov 1, 2025
Summary: This diff optimizes KeyedJaggedTensor.to_dict by optionally removing several unnecessary offset computation. It can evidently improve latency if offsets are not needed in the outputs. Differential Revision: D85995629
coufon
force-pushed
the
export-D85995629
branch
from
d2347fc to
101e253
Compare
coufon
added a commit
to coufon/torchrec
that referenced
this pull request
Nov 1, 2025
Summary: This diff optimizes KeyedJaggedTensor.to_dict by optionally removing several unnecessary offset computation. It can evidently improve latency if offsets are not needed in the outputs. Differential Revision: D85995629
coufon
force-pushed
the
export-D85995629
branch
from
101e253 to
c229f9f
Compare
coufon
added a commit
to coufon/torchrec
that referenced
this pull request
Nov 2, 2025
Summary: This diff optimizes KeyedJaggedTensor.to_dict by optionally removing several unnecessary offset computation. It can evidently improve latency if offsets are not needed in the outputs. Differential Revision: D85995629
coufon
force-pushed
the
export-D85995629
branch
2 times, most recently
from
0e8f914 to
a76a3b5
Compare
coufon
added a commit
to coufon/torchrec
that referenced
this pull request
Nov 4, 2025
Summary: This diff optimizes KeyedJaggedTensor.to_dict by optionally removing several unnecessary offset computation. It can evidently improve latency if offsets are not needed in the outputs. Differential Revision: D85995629
coufon
added a commit
to coufon/torchrec
that referenced
this pull request
Nov 4, 2025
Summary: This diff optimizes KeyedJaggedTensor.to_dict by optionally removing several unnecessary offset computation. It can evidently improve latency if offsets are not needed in the outputs. Differential Revision: D85995629
coufon
force-pushed
the
export-D85995629
branch
from
a76a3b5 to
2556222
Compare
Summary: This diff optimizes KeyedJaggedTensor.to_dict by optionally removing several unnecessary offset computation. It can evidently improve latency if offsets are not needed in the outputs. Reviewed By: guowentian Differential Revision: D85995629
coufon
force-pushed
the
export-D85995629
branch
from
2556222 to
412ed27
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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: This diff optimizes KeyedJaggedTensor.to_dict by optionally removing several unnecessary offset computation. It can evidently improve latency if offsets are not needed in the outputs.
Differential Revision: D85995629