Extend support for scalars and scalar lists in Value class #2271
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/2271
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New Failure, 1 Unrelated FailureAs of commit 066f119 with merge base c0167c5 ( NEW FAILURE - The following job has failed:
BROKEN TRUNK - The following job failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D54561567 |
SS-JIA
added a commit
to SS-JIA/executorch-1
that referenced
this pull request
Mar 6, 2024
) Summary: ## Context This changeset enables serialization and execution of Operators with arbitrary function signatures. Previously, only operators with a very specific schema were supported (2 inputs, 1 output). This is achieved by extending the `Value` class (which is essentially a tagged union) to support all necessary types. All objects needed to execute an operator are now serialized/deserialized as a tagged union. This changeset also refactors `VulkanBackend.cpp` by introducing `GraphBuilder` which makes constructing a `ComputeGraph` from a serialized flatbuffer much clearer. Differential Revision: D54561567
|
This pull request was exported from Phabricator. Differential Revision: D54561567 |
SS-JIA
added a commit
to SS-JIA/executorch-1
that referenced
this pull request
Mar 6, 2024
) Summary: ## Context This changeset enables serialization and execution of Operators with arbitrary function signatures. Previously, only operators with a very specific schema were supported (2 inputs, 1 output). This is achieved by extending the `Value` class (which is essentially a tagged union) to support all necessary types. All objects needed to execute an operator are now serialized/deserialized as a tagged union. This changeset also refactors `VulkanBackend.cpp` by introducing `GraphBuilder` which makes constructing a `ComputeGraph` from a serialized flatbuffer much clearer. Differential Revision: D54561567
|
This pull request was exported from Phabricator. Differential Revision: D54561567 |
SS-JIA
added a commit
to SS-JIA/executorch-1
that referenced
this pull request
Mar 6, 2024
) Summary: ## Context This changeset enables serialization and execution of Operators with arbitrary function signatures. Previously, only operators with a very specific schema were supported (2 inputs, 1 output). This is achieved by extending the `Value` class (which is essentially a tagged union) to support all necessary types. All objects needed to execute an operator are now serialized/deserialized as a tagged union. This changeset also refactors `VulkanBackend.cpp` by introducing `GraphBuilder` which makes constructing a `ComputeGraph` from a serialized flatbuffer much clearer. Differential Revision: D54561567
|
This pull request was exported from Phabricator. Differential Revision: D54561567 |
SS-JIA
added a commit
to SS-JIA/executorch-1
that referenced
this pull request
Mar 6, 2024
) Summary: ## Context This changeset enables serialization and execution of Operators with arbitrary function signatures. Previously, only operators with a very specific schema were supported (2 inputs, 1 output). This is achieved by extending the `Value` class (which is essentially a tagged union) to support all necessary types. All objects needed to execute an operator are now serialized/deserialized as a tagged union. This changeset also refactors `VulkanBackend.cpp` by introducing `GraphBuilder` which makes constructing a `ComputeGraph` from a serialized flatbuffer much clearer. Differential Revision: D54561567
|
This pull request was exported from Phabricator. Differential Revision: D54561567 |
SS-JIA
added a commit
to SS-JIA/executorch-1
that referenced
this pull request
Mar 6, 2024
) Summary: ## Context This changeset enables serialization and execution of Operators with arbitrary function signatures. Previously, only operators with a very specific schema were supported (2 inputs, 1 output). This is achieved by extending the `Value` class (which is essentially a tagged union) to support all necessary types. All objects needed to execute an operator are now serialized/deserialized as a tagged union. This changeset also refactors `VulkanBackend.cpp` by introducing `GraphBuilder` which makes constructing a `ComputeGraph` from a serialized flatbuffer much clearer. Differential Revision: D54561567
|
This pull request was exported from Phabricator. Differential Revision: D54561567 |
jorgep31415
approved these changes
Mar 6, 2024
) Summary: ## Context This changeset enables serialization and execution of Operators with arbitrary function signatures. Previously, only operators with a very specific schema were supported (2 inputs, 1 output). This is achieved by extending the `Value` class (which is essentially a tagged union) to support all necessary types. All objects needed to execute an operator are now serialized/deserialized as a tagged union. This changeset also refactors `VulkanBackend.cpp` by introducing `GraphBuilder` which makes constructing a `ComputeGraph` from a serialized flatbuffer much clearer. Reviewed By: jorgep31415 Differential Revision: D54561567
SS-JIA
added a commit
to SS-JIA/executorch-1
that referenced
this pull request
Mar 6, 2024
) Summary: ## Context This changeset enables serialization and execution of Operators with arbitrary function signatures. Previously, only operators with a very specific schema were supported (2 inputs, 1 output). This is achieved by extending the `Value` class (which is essentially a tagged union) to support all necessary types. All objects needed to execute an operator are now serialized/deserialized as a tagged union. This changeset also refactors `VulkanBackend.cpp` by introducing `GraphBuilder` which makes constructing a `ComputeGraph` from a serialized flatbuffer much clearer. Reviewed By: jorgep31415 Differential Revision: D54561567
|
This pull request was exported from Phabricator. Differential Revision: D54561567 |
|
This pull request was exported from Phabricator. Differential Revision: D54561567 |
|
This pull request has been merged in 12fcfcf. |
jorgep31415
added a commit
that referenced
this pull request
Mar 13, 2024
In #2271, we already added - IntList - DoubleList - BoolList - ValueList to the schema and the runtime's Value class. Their serialization was incomplete missing two components: 1. Receiving a list in `torch.fx.Node.args`. 2. Receiving a non-tensor in `torch.fx.Node`. This change completes #1. Also, this change fixes a bug where values type `bool` matches both types `bool` and `int` and hence were being added twice. If our type support grows more complex, we can consider using our own types similar to the core Executorch runtime: https://github.com/pytorch/executorch/blob/689796499024fc4a133318d707f4c10db73da967/exir/emit/_emitter.py#L158-L166 Differential Revision: [D54708353](https://our.internmc.facebook.com/intern/diff/D54708353/) [ghstack-poisoned]
jorgep31415
added a commit
that referenced
this pull request
Mar 13, 2024
In #2271, we already added - IntList - DoubleList - BoolList - ValueList to the schema and the runtime's Value class. Their serialization was incomplete missing two components: 1. Receiving a list in `torch.fx.Node.args`. 2. Receiving a non-tensor in `torch.fx.Node`. This change completes #2. Also, we introduce a specific handler for `getitem` nodes as it is required. Every `function_call` outputting non-tensor `torch.fx.Node` is followed by a special `getitem` `function_call`. Differential Revision: [D54789099](https://our.internmc.facebook.com/intern/diff/D54789099/) [ghstack-poisoned]
jorgep31415
added a commit
that referenced
this pull request
Mar 13, 2024
In #2271, we already added - IntList - DoubleList - BoolList - ValueList to the schema and the runtime's Value class. Their serialization was incomplete missing two components: 1. Receiving a list in `torch.fx.Node.args`. 2. Receiving a non-tensor in `torch.fx.Node`. This change completes #2. Also, we introduce a specific handler for `getitem` nodes as it is required. Every `function_call` outputting non-tensor `torch.fx.Node` is followed by a special `getitem` `function_call`. Differential Revision: [D54789099](https://our.internmc.facebook.com/intern/diff/D54789099/) ghstack-source-id: 218541429 Pull Request resolved: #2405
facebook-github-bot
pushed a commit
that referenced
this pull request
Mar 13, 2024
Summary: bypass-github-export-checks Pull Request resolved: #2404 In #2271, we already added - IntList - DoubleList - BoolList - ValueList to the schema and the runtime's Value class. Their serialization was incomplete missing two components: 1. Receiving a list in `torch.fx.Node.args`. 2. Receiving a non-tensor in `torch.fx.Node`. This change completes #1. Also, this change fixes a bug where values type `bool` matches both types `bool` and `int` and hence were being added twice. If our type support grows more complex, we can consider using our own types similar to the core Executorch runtime: https://github.com/pytorch/executorch/blob/689796499024fc4a133318d707f4c10db73da967/exir/emit/_emitter.py#L158-L166 ghstack-source-id: 218539049 exported-using-ghexport Reviewed By: SS-JIA Differential Revision: D54708353 fbshipit-source-id: 8641647b515e201ea63db67115c01c1532ad6566
facebook-github-bot
pushed a commit
that referenced
this pull request
Mar 13, 2024
Summary: bypass-github-export-checks Pull Request resolved: #2405 In #2271, we already added - IntList - DoubleList - BoolList - ValueList to the schema and the runtime's Value class. Their serialization was incomplete missing two components: 1. Receiving a list in `torch.fx.Node.args`. 2. Receiving a non-tensor in `torch.fx.Node`. This change completes #2. Also, we introduce a specific handler for `getitem` nodes as it is required. Every `function_call` outputting non-tensor `torch.fx.Node` is followed by a special `getitem` `function_call`. ghstack-source-id: 218541429 exported-using-ghexport Reviewed By: SS-JIA Differential Revision: D54789099 fbshipit-source-id: 1e58cbc0246a8c651d95e9ef6707bacb60066e2b
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:
Context
This changeset enables serialization and execution of Operators with arbitrary function signatures. Previously, only operators with a very specific schema were supported (2 inputs, 1 output).
This is achieved by extending the
Valueclass (which is essentially a tagged union) to support all necessary types. All objects needed to execute an operator are now serialized/deserialized as a tagged union.This changeset also refactors
VulkanBackend.cppby introducingGraphBuilderwhich makes constructing aComputeGraphfrom a serialized flatbuffer much clearer.Differential Revision: D54561567