Demo backend #1
Closed
Demo backend #1
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
Summary: Pull Request resolved: pytorch#1002 exir.capture is deprecated. Update etrecord.bin to align with new serialization schema Deprecation warning will still trigger at runtime due to `executorch.exir.tests.models` import. Reviewed By: Jack-Khuu Differential Revision: D50378335 fbshipit-source-id: e8511f6ed91dab84a600ff70077b73f909dd551b
Summary: Pull Request resolved: pytorch#1047 Reviewed By: SS-JIA, kirklandsign Differential Revision: D50562878 Pulled By: digantdesai fbshipit-source-id: cb83cc9b2e3113ae170fb3eb997d2ca205b38908
Summary: Pull Request resolved: pytorch#1072 When reading this, "perform the same action" made it sound like these steps would also create an `add.pte` file, but that's not true. I looked into adding the code that would actually perform the exact same action, but the AddModule isn't in exir.tests. So, instead just call out that it's not literally the same action. While I'm here: - Remove the `>>>` so that users can copy and paste all of the lines at once - Remove the `print`, which just printed something like `<executorch.exir.program._program.ExirExportedProgram object at 0x102f1ae00>` Reviewed By: angelayi Differential Revision: D50578857 fbshipit-source-id: b0303b7c847572b33809781642680a16e8415eab
Summary: fixed pytorch#677 simplified and made binary format more robust/validate-able and moved more processing to AoT made runtime input/output support more general (arbitrary number of EValue inputs and outputs) Pull Request resolved: pytorch#1046 Reviewed By: SS-JIA Differential Revision: D50599184 Pulled By: digantdesai fbshipit-source-id: 908d8598745b0b4b99c4001cc42c6a74c251e563
Summary: Run XNNPACK (delegation-only, quantization-only, delegation+quantization) on a single workflow to save the number of jobs. Pull Request resolved: pytorch#1071 Reviewed By: huydhn Differential Revision: D50580091 Pulled By: kirklandsign fbshipit-source-id: 6b750a818497cb42739b91492fa137b7d1518e64
kirklandsign
pushed a commit
that referenced
this pull request
Mar 12, 2024
Summary: bypass-github-export-checks Pull Request resolved: pytorch#2348 Before: Each node contains a `UniformParamsBuffer`. After: Each node contains a `std::vector<std::shared_ptr<UniformParamsBuffer>>`. In follow up changes, we will break up parameters to be passed via multiple UniformParamsBuffer, since 1. some are tensor-specific (e.g. image extents) and 2. others are operator-specific (e.g. alpha for binary ops). Hence, we need **`std::vector`**. We are adding the methods for #1 in pytorch#2340. Since #1 and #2 will be owned by different objects, we need **pointers**. Since #1 is owned by `vTensor` which is non-copyable, we can't use unique_ptr so we need **`std::shared_ptr`**. ghstack-source-id: 218195447 exported-using-ghexport Reviewed By: SS-JIA Differential Revision: D54691831 fbshipit-source-id: 84ab9f777e247fd56234290ed7f7343b9701c73f
kirklandsign
pushed a commit
that referenced
this pull request
Mar 15, 2024
Summary: bypass-github-export-checks Pull Request resolved: pytorch#2404 In pytorch#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
kirklandsign
pushed a commit
that referenced
this pull request
May 29, 2024
Summary: Pull Request resolved: pytorch#3763 Reviewed By: itamaro, tarun292 Differential Revision: D51566750 fbshipit-source-id: 654c426d479833867e93083e9b55786abfc24a32
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.
No description provided.