Fix collection inputs to postproc modules #2733
Open
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: D69292525 |
che-sh
force-pushed
the
export-D69292525
branch
from
f9b4c11 to
a4200a6
Compare
che-sh
added a commit
to che-sh/torchrec
that referenced
this pull request
Feb 11, 2025
Summary:
Postproc modules with collection inputs (list or dict) with non-static (derived from input or other postproc) elements were not properly rewritten - input elements remained fx.Nodes even during the actual model forward (i.e. outside rewrite, during pipeline execution)
To illustrate:
```
def forward(model_input: ...) -> ...:
modified_input = model_input.float_features + 1
sharded_module_input = self.postproc(model_input, modified_input) # works
sharded_module_input = self.postproc(model_input, [123]) # works
sharded_module_input = self.postproc(model_input, [torch.ones_like(modified_input)]) # fails
sharded_module_input = self.postproc(model_input, [modified_input]) # fails
sharded_module_input = self.postproc(model_input, { 'a': 123 }) # works
sharded_module_input = self.postproc(model_input, { 'a': torch.ones_like(modified_input) }) # fails
sharded_module_input = self.postproc(model_input, { 'a': modified_input }) # fails
return self.ebc(sharded_module_input)
```
Differential Revision: D69292525
|
This pull request was exported from Phabricator. Differential Revision: D69292525 |
che-sh
added a commit
to che-sh/torchrec
that referenced
this pull request
Feb 11, 2025
…postproc modules (pytorch#2733) Summary: Postproc modules with collection inputs (list or dict) with non-static (derived from input or other postproc) elements were not properly rewritten - input elements remained fx.Nodes even during the actual model forward (i.e. outside rewrite, during pipeline execution) To illustrate: ``` def forward(model_input: ...) -> ...: modified_input = model_input.float_features + 1 sharded_module_input = self.postproc(model_input, modified_input) # works sharded_module_input = self.postproc(model_input, [123]) # works sharded_module_input = self.postproc(model_input, [torch.ones_like(modified_input)]) # fails sharded_module_input = self.postproc(model_input, [modified_input]) # fails sharded_module_input = self.postproc(model_input, { 'a': 123 }) # works sharded_module_input = self.postproc(model_input, { 'a': torch.ones_like(modified_input) }) # fails sharded_module_input = self.postproc(model_input, { 'a': modified_input }) # fails return self.ebc(sharded_module_input) ``` Differential Revision: D69292525
che-sh
force-pushed
the
export-D69292525
branch
from
a4200a6 to
17b0810
Compare
|
This pull request was exported from Phabricator. Differential Revision: D69292525 |
che-sh
force-pushed
the
export-D69292525
branch
from
17b0810 to
9066e6b
Compare
che-sh
added a commit
to che-sh/torchrec
that referenced
this pull request
Feb 12, 2025
…stproc modules (pytorch#2733) Summary: Postproc modules with collection inputs (list or dict) with non-static (derived from input or other postproc) elements were not properly rewritten - input elements remained fx.Nodes even during the actual model forward (i.e. outside rewrite, during pipeline execution) To illustrate: ``` def forward(model_input: ...) -> ...: modified_input = model_input.float_features + 1 sharded_module_input = self.postproc(model_input, modified_input) # works sharded_module_input = self.postproc(model_input, [123]) # works sharded_module_input = self.postproc(model_input, [torch.ones_like(modified_input)]) # fails sharded_module_input = self.postproc(model_input, [modified_input]) # fails sharded_module_input = self.postproc(model_input, { 'a': 123 }) # works sharded_module_input = self.postproc(model_input, { 'a': torch.ones_like(modified_input) }) # fails sharded_module_input = self.postproc(model_input, { 'a': modified_input }) # fails return self.ebc(sharded_module_input) ``` Differential Revision: D69292525
|
This pull request was exported from Phabricator. Differential Revision: D69292525 |
che-sh
added a commit
to che-sh/torchrec
that referenced
this pull request
Feb 12, 2025
…stproc modules (pytorch#2733) Summary: Postproc modules with collection inputs (list or dict) with non-static (derived from input or other postproc) elements were not properly rewritten - input elements remained fx.Nodes even during the actual model forward (i.e. outside rewrite, during pipeline execution) To illustrate: ``` def forward(model_input: ...) -> ...: modified_input = model_input.float_features + 1 sharded_module_input = self.postproc(model_input, modified_input) # works sharded_module_input = self.postproc(model_input, [123]) # works sharded_module_input = self.postproc(model_input, [torch.ones_like(modified_input)]) # fails sharded_module_input = self.postproc(model_input, [modified_input]) # fails sharded_module_input = self.postproc(model_input, { 'a': 123 }) # works sharded_module_input = self.postproc(model_input, { 'a': torch.ones_like(modified_input) }) # fails sharded_module_input = self.postproc(model_input, { 'a': modified_input }) # fails return self.ebc(sharded_module_input) ``` Differential Revision: D69292525
che-sh
added a commit
to che-sh/torchrec
that referenced
this pull request
Feb 12, 2025
…stproc modules (pytorch#2733) Summary: Postproc modules with collection inputs (list or dict) with non-static (derived from input or other postproc) elements were not properly rewritten - input elements remained fx.Nodes even during the actual model forward (i.e. outside rewrite, during pipeline execution) To illustrate: ``` def forward(model_input: ...) -> ...: modified_input = model_input.float_features + 1 sharded_module_input = self.postproc(model_input, modified_input) # works sharded_module_input = self.postproc(model_input, [123]) # works sharded_module_input = self.postproc(model_input, [torch.ones_like(modified_input)]) # fails sharded_module_input = self.postproc(model_input, [modified_input]) # fails sharded_module_input = self.postproc(model_input, { 'a': 123 }) # works sharded_module_input = self.postproc(model_input, { 'a': torch.ones_like(modified_input) }) # fails sharded_module_input = self.postproc(model_input, { 'a': modified_input }) # fails return self.ebc(sharded_module_input) ``` Differential Revision: D69292525
che-sh
added a commit
to che-sh/torchrec
that referenced
this pull request
Feb 13, 2025
…stproc modules (pytorch#2733) Summary: Postproc modules with collection inputs (list or dict) with non-static (derived from input or other postproc) elements were not properly rewritten - input elements remained fx.Nodes even during the actual model forward (i.e. outside rewrite, during pipeline execution) To illustrate: ``` def forward(model_input: ...) -> ...: modified_input = model_input.float_features + 1 sharded_module_input = self.postproc(model_input, modified_input) # works sharded_module_input = self.postproc(model_input, [123]) # works sharded_module_input = self.postproc(model_input, [torch.ones_like(modified_input)]) # fails sharded_module_input = self.postproc(model_input, [modified_input]) # fails sharded_module_input = self.postproc(model_input, { 'a': 123 }) # works sharded_module_input = self.postproc(model_input, { 'a': torch.ones_like(modified_input) }) # fails sharded_module_input = self.postproc(model_input, { 'a': modified_input }) # fails return self.ebc(sharded_module_input) ``` Differential Revision: D69292525
che-sh
added a commit
to che-sh/torchrec
that referenced
this pull request
Feb 13, 2025
…stproc modules (pytorch#2733) Summary: Postproc modules with collection inputs (list or dict) with non-static (derived from input or other postproc) elements were not properly rewritten - input elements remained fx.Nodes even during the actual model forward (i.e. outside rewrite, during pipeline execution) To illustrate: ``` def forward(model_input: ...) -> ...: modified_input = model_input.float_features + 1 sharded_module_input = self.postproc(model_input, modified_input) # works sharded_module_input = self.postproc(model_input, [123]) # works sharded_module_input = self.postproc(model_input, [torch.ones_like(modified_input)]) # fails sharded_module_input = self.postproc(model_input, [modified_input]) # fails sharded_module_input = self.postproc(model_input, { 'a': 123 }) # works sharded_module_input = self.postproc(model_input, { 'a': torch.ones_like(modified_input) }) # fails sharded_module_input = self.postproc(model_input, { 'a': modified_input }) # fails return self.ebc(sharded_module_input) ``` Differential Revision: D69292525
che-sh
force-pushed
the
export-D69292525
branch
from
9066e6b to
5bcc494
Compare
|
This pull request was exported from Phabricator. Differential Revision: D69292525 |
che-sh
added a commit
to che-sh/torchrec
that referenced
this pull request
Feb 13, 2025
…stproc modules (pytorch#2733) Summary: Postproc modules with collection inputs (list or dict) with non-static (derived from input or other postproc) elements were not properly rewritten - input elements remained fx.Nodes even during the actual model forward (i.e. outside rewrite, during pipeline execution) To illustrate: ``` def forward(model_input: ...) -> ...: modified_input = model_input.float_features + 1 sharded_module_input = self.postproc(model_input, modified_input) # works sharded_module_input = self.postproc(model_input, [123]) # works sharded_module_input = self.postproc(model_input, [torch.ones_like(modified_input)]) # fails sharded_module_input = self.postproc(model_input, [modified_input]) # fails sharded_module_input = self.postproc(model_input, { 'a': 123 }) # works sharded_module_input = self.postproc(model_input, { 'a': torch.ones_like(modified_input) }) # fails sharded_module_input = self.postproc(model_input, { 'a': modified_input }) # fails return self.ebc(sharded_module_input) ``` Differential Revision: D69292525
che-sh
added a commit
to che-sh/torchrec
that referenced
this pull request
Feb 13, 2025
…stproc modules (pytorch#2733) Summary: Postproc modules with collection inputs (list or dict) with non-static (derived from input or other postproc) elements were not properly rewritten - input elements remained fx.Nodes even during the actual model forward (i.e. outside rewrite, during pipeline execution) To illustrate: ``` def forward(model_input: ...) -> ...: modified_input = model_input.float_features + 1 sharded_module_input = self.postproc(model_input, modified_input) # works sharded_module_input = self.postproc(model_input, [123]) # works sharded_module_input = self.postproc(model_input, [torch.ones_like(modified_input)]) # fails sharded_module_input = self.postproc(model_input, [modified_input]) # fails sharded_module_input = self.postproc(model_input, { 'a': 123 }) # works sharded_module_input = self.postproc(model_input, { 'a': torch.ones_like(modified_input) }) # fails sharded_module_input = self.postproc(model_input, { 'a': modified_input }) # fails return self.ebc(sharded_module_input) ``` Differential Revision: D69292525
che-sh
added a commit
to che-sh/torchrec
that referenced
this pull request
Feb 13, 2025
…stproc modules (pytorch#2733) Summary: Postproc modules with collection inputs (list or dict) with non-static (derived from input or other postproc) elements were not properly rewritten - input elements remained fx.Nodes even during the actual model forward (i.e. outside rewrite, during pipeline execution) To illustrate: ``` def forward(model_input: ...) -> ...: modified_input = model_input.float_features + 1 sharded_module_input = self.postproc(model_input, modified_input) # works sharded_module_input = self.postproc(model_input, [123]) # works sharded_module_input = self.postproc(model_input, [torch.ones_like(modified_input)]) # fails sharded_module_input = self.postproc(model_input, [modified_input]) # fails sharded_module_input = self.postproc(model_input, { 'a': 123 }) # works sharded_module_input = self.postproc(model_input, { 'a': torch.ones_like(modified_input) }) # fails sharded_module_input = self.postproc(model_input, { 'a': modified_input }) # fails return self.ebc(sharded_module_input) ``` Differential Revision: D69292525
che-sh
added a commit
to che-sh/torchrec
that referenced
this pull request
Feb 13, 2025
…stproc modules (pytorch#2733) Summary: Postproc modules with collection inputs (list or dict) with non-static (derived from input or other postproc) elements were not properly rewritten - input elements remained fx.Nodes even during the actual model forward (i.e. outside rewrite, during pipeline execution) To illustrate: ``` def forward(model_input: ...) -> ...: modified_input = model_input.float_features + 1 sharded_module_input = self.postproc(model_input, modified_input) # works sharded_module_input = self.postproc(model_input, [123]) # works sharded_module_input = self.postproc(model_input, [torch.ones_like(modified_input)]) # fails sharded_module_input = self.postproc(model_input, [modified_input]) # fails sharded_module_input = self.postproc(model_input, { 'a': 123 }) # works sharded_module_input = self.postproc(model_input, { 'a': torch.ones_like(modified_input) }) # fails sharded_module_input = self.postproc(model_input, { 'a': modified_input }) # fails return self.ebc(sharded_module_input) ``` Differential Revision: D69292525
che-sh
added a commit
to che-sh/torchrec
that referenced
this pull request
Feb 13, 2025
…stproc modules (pytorch#2733) Summary: Postproc modules with collection inputs (list or dict) with non-static (derived from input or other postproc) elements were not properly rewritten - input elements remained fx.Nodes even during the actual model forward (i.e. outside rewrite, during pipeline execution) To illustrate: ``` def forward(model_input: ...) -> ...: modified_input = model_input.float_features + 1 sharded_module_input = self.postproc(model_input, modified_input) # works sharded_module_input = self.postproc(model_input, [123]) # works sharded_module_input = self.postproc(model_input, [torch.ones_like(modified_input)]) # fails sharded_module_input = self.postproc(model_input, [modified_input]) # fails sharded_module_input = self.postproc(model_input, { 'a': 123 }) # works sharded_module_input = self.postproc(model_input, { 'a': torch.ones_like(modified_input) }) # fails sharded_module_input = self.postproc(model_input, { 'a': modified_input }) # fails return self.ebc(sharded_module_input) ``` Differential Revision: D69292525
Summary: `_shard_modules` function is used in fx_traceability tests for SDD and SemiSync pipeline. It uses a default ShardingPlanner and topology that use hardcoded batch size (512) and HBM memory limit (32Gb), respectively. This change allows specifying the ShardingPlanner and Topology to more accurately reflect the machine capabilities. The change is intentionally limited to `_shard_modules` only and not public `shard_modules` to avoid changing the contract for the latter. Reviewed By: sarckk Differential Revision: D69163227
…stproc modules (pytorch#2733) Summary: Postproc modules with collection inputs (list or dict) with non-static (derived from input or other postproc) elements were not properly rewritten - input elements remained fx.Nodes even during the actual model forward (i.e. outside rewrite, during pipeline execution) To illustrate: ``` def forward(model_input: ...) -> ...: modified_input = model_input.float_features + 1 sharded_module_input = self.postproc(model_input, modified_input) # works sharded_module_input = self.postproc(model_input, [123]) # works sharded_module_input = self.postproc(model_input, [torch.ones_like(modified_input)]) # fails sharded_module_input = self.postproc(model_input, [modified_input]) # fails sharded_module_input = self.postproc(model_input, { 'a': 123 }) # works sharded_module_input = self.postproc(model_input, { 'a': torch.ones_like(modified_input) }) # fails sharded_module_input = self.postproc(model_input, { 'a': modified_input }) # fails return self.ebc(sharded_module_input) ``` Differential Revision: D69292525
che-sh
force-pushed
the
export-D69292525
branch
from
5bcc494 to
0aedf8b
Compare
|
This pull request was exported from Phabricator. Differential Revision: D69292525 |
che-sh
added a commit
to che-sh/torchrec
that referenced
this pull request
Feb 14, 2025
…stproc modules (pytorch#2733) Summary: Postproc modules with collection inputs (list or dict) with non-static (derived from input or other postproc) elements were not properly rewritten - input elements remained fx.Nodes even during the actual model forward (i.e. outside rewrite, during pipeline execution) To illustrate: ``` def forward(model_input: ...) -> ...: modified_input = model_input.float_features + 1 sharded_module_input = self.postproc(model_input, modified_input) # works sharded_module_input = self.postproc(model_input, [123]) # works sharded_module_input = self.postproc(model_input, [torch.ones_like(modified_input)]) # fails sharded_module_input = self.postproc(model_input, [modified_input]) # fails sharded_module_input = self.postproc(model_input, { 'a': 123 }) # works sharded_module_input = self.postproc(model_input, { 'a': torch.ones_like(modified_input) }) # fails sharded_module_input = self.postproc(model_input, { 'a': modified_input }) # fails return self.ebc(sharded_module_input) ``` Differential Revision: D69292525
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:
Postproc modules with collection inputs (list or dict) with non-static (derived from input or other postproc) elements were not properly rewritten - input elements remained fx.Nodes even during the actual model forward (i.e. outside rewrite, during pipeline execution)
To illustrate: