[executorch][runtime] Introduce PteDataMap for weight sharing #8887
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
PteDataMap is the NamedDataMap that will live in the runtime. It is used to give delegates access to opaque named data stored in the PTE file. Open to alternative naming suggestions, maybe 'PTEDataMap' or 'ProgramDataMap'? **Usage** The PteDataMap is owned by the program, and instantiated at program load time if named_data exists in the PTE file. We introduce usage of 'std::optional' here. I think we can also use executorch::aten::optional to avoid adding standard lib ? When initializing delegates, the PteDataMap is given to delegate_init. Delegates can retrieve opaque delegate data by key using 'get_data'. This gives them a FreeableBuffer that they can free later. **Testing** This test uses the C++ flatbuffer API to build a fake program containing named data. We also creates a temp file with sample data that the data loader can wrap around. TODO: e2e test once delegate aot is ready and we can generate a file with named data. **Note** As the PteDataMap wraps around flatbuffer constructs, the Program must outlive the PteDataMap. PteDataMap does not implement - get_metadata; currently, all data stored is opaque. Later, we can implement get_metadata if a backend stores plain tensor data. - load_into; this is mostly used for the training case, and isn't used by delegates, at least not at the moment Differential Revision: [D70213646](https://our.internmc.facebook.com/intern/diff/D70213646/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/8887
Note: Links to docs will display an error until the docs builds have been completed. ⏳ No Failures, 1 PendingAs of commit 44d9570 with merge base fe69e29 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
lucylq
added a commit
that referenced
this pull request
Mar 3, 2025
PteDataMap is the NamedDataMap that will live in the runtime. It is used to give delegates access to opaque named data stored in the PTE file. Open to alternative naming suggestions, maybe 'PTEDataMap' or 'ProgramDataMap'? **Usage** The PteDataMap is owned by the program, and instantiated at program load time if named_data exists in the PTE file. We introduce usage of 'std::optional' here. I think we can also use executorch::aten::optional to avoid adding standard lib ? When initializing delegates, the PteDataMap is given to delegate_init. Delegates can retrieve opaque delegate data by key using 'get_data'. This gives them a FreeableBuffer that they can free later. **Testing** This test uses the C++ flatbuffer API to build a fake program containing named data. We also creates a temp file with sample data that the data loader can wrap around. TODO: e2e test once delegate aot is ready and we can generate a file with named data. **Note** As the PteDataMap wraps around flatbuffer constructs, the Program must outlive the PteDataMap. PteDataMap does not implement - get_metadata; currently, all data stored is opaque. Later, we can implement get_metadata if a backend stores plain tensor data. - load_into; this is mostly used for the training case, and isn't used by delegates, at least not at the moment Differential Revision: [D70213646](https://our.internmc.facebook.com/intern/diff/D70213646/) ghstack-source-id: 269379135 Pull Request resolved: #8887
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D70213646 |
…ing" PteDataMap is the NamedDataMap that will live in the runtime. It is used to give delegates access to opaque named data stored in the PTE file. Open to alternative naming suggestions, maybe 'PTEDataMap' or 'ProgramDataMap'? **Usage** The PteDataMap is owned by the program, and instantiated at program load time if named_data exists in the PTE file. We introduce usage of 'std::optional' here. I think we can also use executorch::aten::optional to avoid adding standard lib ? When initializing delegates, the PteDataMap is given to delegate_init. Delegates can retrieve opaque delegate data by key using 'get_data'. This gives them a FreeableBuffer that they can free later. **Testing** This test uses the C++ flatbuffer API to build a fake program containing named data. We also creates a temp file with sample data that the data loader can wrap around. TODO: e2e test once delegate aot is ready and we can generate a file with named data. **Note** As the PteDataMap wraps around flatbuffer constructs, the Program must outlive the PteDataMap. PteDataMap does not implement - get_metadata; currently, all data stored is opaque. Later, we can implement get_metadata if a backend stores plain tensor data. - load_into; this is mostly used for the training case, and isn't used by delegates, at least not at the moment Differential Revision: [D70213646](https://our.internmc.facebook.com/intern/diff/D70213646/) [ghstack-poisoned]
lucylq
added a commit
that referenced
this pull request
Mar 3, 2025
Pull Request resolved: #8887 PteDataMap is the NamedDataMap that will live in the runtime. It is used to give delegates access to opaque named data stored in the PTE file. Open to alternative naming suggestions, maybe 'PTEDataMap' or 'ProgramDataMap'? **Usage** The PteDataMap is owned by the program, and instantiated at program load time if named_data exists in the PTE file. We introduce usage of 'std::optional' here. I think we can also use executorch::aten::optional to avoid adding standard lib ? When initializing delegates, the PteDataMap is given to delegate_init. Delegates can retrieve opaque delegate data by key using 'get_data'. This gives them a FreeableBuffer that they can free later. **Testing** This test uses the C++ flatbuffer API to build a fake program containing named data. We also creates a temp file with sample data that the data loader can wrap around. TODO: e2e test once delegate aot is ready and we can generate a file with named data. **Note** As the PteDataMap wraps around flatbuffer constructs, the Program must outlive the PteDataMap. PteDataMap does not implement - get_metadata; currently, all data stored is opaque. Later, we can implement get_metadata if a backend stores plain tensor data. - load_into; this is mostly used for the training case, and isn't used by delegates, at least not at the moment Differential Revision: [D70213646](https://our.internmc.facebook.com/intern/diff/D70213646/) ghstack-source-id: 269379135
lucylq
added
the
release notes: runtime
…ing" PteDataMap is the NamedDataMap that will live in the runtime. It is used to give delegates access to opaque named data stored in the PTE file. Open to alternative naming suggestions, maybe 'PTEDataMap' or 'ProgramDataMap'? **Usage** The PteDataMap is owned by the program, and instantiated at program load time if named_data exists in the PTE file. We introduce usage of 'std::optional' here. I think we can also use executorch::aten::optional to avoid adding standard lib ? When initializing delegates, the PteDataMap is given to delegate_init. Delegates can retrieve opaque delegate data by key using 'get_data'. This gives them a FreeableBuffer that they can free later. **Testing** This test uses the C++ flatbuffer API to build a fake program containing named data. We also creates a temp file with sample data that the data loader can wrap around. TODO: e2e test once delegate aot is ready and we can generate a file with named data. **Note** As the PteDataMap wraps around flatbuffer constructs, the Program must outlive the PteDataMap. PteDataMap does not implement - get_metadata; currently, all data stored is opaque. Later, we can implement get_metadata if a backend stores plain tensor data. - load_into; this is mostly used for the training case, and isn't used by delegates, at least not at the moment Differential Revision: [D70213646](https://our.internmc.facebook.com/intern/diff/D70213646/) [ghstack-poisoned]
lucylq
added a commit
that referenced
this pull request
Mar 3, 2025
Pull Request resolved: #8887 PteDataMap is the NamedDataMap that will live in the runtime. It is used to give delegates access to opaque named data stored in the PTE file. Open to alternative naming suggestions, maybe 'PTEDataMap' or 'ProgramDataMap'? **Usage** The PteDataMap is owned by the program, and instantiated at program load time if named_data exists in the PTE file. We introduce usage of 'std::optional' here. I think we can also use executorch::aten::optional to avoid adding standard lib ? When initializing delegates, the PteDataMap is given to delegate_init. Delegates can retrieve opaque delegate data by key using 'get_data'. This gives them a FreeableBuffer that they can free later. **Testing** This test uses the C++ flatbuffer API to build a fake program containing named data. We also creates a temp file with sample data that the data loader can wrap around. TODO: e2e test once delegate aot is ready and we can generate a file with named data. **Note** As the PteDataMap wraps around flatbuffer constructs, the Program must outlive the PteDataMap. PteDataMap does not implement - get_metadata; currently, all data stored is opaque. Later, we can implement get_metadata if a backend stores plain tensor data. - load_into; this is mostly used for the training case, and isn't used by delegates, at least not at the moment Differential Revision: [D70213646](https://our.internmc.facebook.com/intern/diff/D70213646/) ghstack-source-id: 269464629
…ing" PteDataMap is the NamedDataMap that will live in the runtime. It is used to give delegates access to opaque named data stored in the PTE file. Open to alternative naming suggestions, maybe 'PTEDataMap' or 'ProgramDataMap'? **Usage** The PteDataMap is owned by the program, and instantiated at program load time if named_data exists in the PTE file. We introduce usage of 'std::optional' here. I think we can also use executorch::aten::optional to avoid adding standard lib ? When initializing delegates, the PteDataMap is given to delegate_init. Delegates can retrieve opaque delegate data by key using 'get_data'. This gives them a FreeableBuffer that they can free later. **Testing** This test uses the C++ flatbuffer API to build a fake program containing named data. We also creates a temp file with sample data that the data loader can wrap around. TODO: e2e test once delegate aot is ready and we can generate a file with named data. **Note** As the PteDataMap wraps around flatbuffer constructs, the Program must outlive the PteDataMap. PteDataMap does not implement - get_metadata; currently, all data stored is opaque. Later, we can implement get_metadata if a backend stores plain tensor data. - load_into; this is mostly used for the training case, and isn't used by delegates, at least not at the moment Differential Revision: [D70213646](https://our.internmc.facebook.com/intern/diff/D70213646/) [ghstack-poisoned]
lucylq
added a commit
that referenced
this pull request
Mar 4, 2025
Pull Request resolved: #8887 PteDataMap is the NamedDataMap that will live in the runtime. It is used to give delegates access to opaque named data stored in the PTE file. Open to alternative naming suggestions, maybe 'PTEDataMap' or 'ProgramDataMap'? **Usage** The PteDataMap is owned by the program, and instantiated at program load time if named_data exists in the PTE file. We introduce usage of 'std::optional' here. I think we can also use executorch::aten::optional to avoid adding standard lib ? When initializing delegates, the PteDataMap is given to delegate_init. Delegates can retrieve opaque delegate data by key using 'get_data'. This gives them a FreeableBuffer that they can free later. **Testing** This test uses the C++ flatbuffer API to build a fake program containing named data. We also creates a temp file with sample data that the data loader can wrap around. TODO: e2e test once delegate aot is ready and we can generate a file with named data. **Note** As the PteDataMap wraps around flatbuffer constructs, the Program must outlive the PteDataMap. PteDataMap does not implement - get_metadata; currently, all data stored is opaque. Later, we can implement get_metadata if a backend stores plain tensor data. - load_into; this is mostly used for the training case, and isn't used by delegates, at least not at the moment Differential Revision: [D70213646](https://our.internmc.facebook.com/intern/diff/D70213646/) ghstack-source-id: 269486949
…ing" PteDataMap is the NamedDataMap that will live in the runtime. It is used to give delegates access to opaque named data stored in the PTE file. Open to alternative naming suggestions, maybe 'PTEDataMap' or 'ProgramDataMap'? **Usage** The PteDataMap is owned by the program, and instantiated at program load time if named_data exists in the PTE file. We introduce usage of 'std::optional' here. I think we can also use executorch::aten::optional to avoid adding standard lib ? When initializing delegates, the PteDataMap is given to delegate_init. Delegates can retrieve opaque delegate data by key using 'get_data'. This gives them a FreeableBuffer that they can free later. **Testing** This test uses the C++ flatbuffer API to build a fake program containing named data. We also creates a temp file with sample data that the data loader can wrap around. TODO: e2e test once delegate aot is ready and we can generate a file with named data. **Note** As the PteDataMap wraps around flatbuffer constructs, the Program must outlive the PteDataMap. PteDataMap does not implement - get_metadata; currently, all data stored is opaque. Later, we can implement get_metadata if a backend stores plain tensor data. - load_into; this is mostly used for the training case, and isn't used by delegates, at least not at the moment Differential Revision: [D70213646](https://our.internmc.facebook.com/intern/diff/D70213646/) [ghstack-poisoned]
lucylq
added a commit
that referenced
this pull request
Mar 4, 2025
Pull Request resolved: #8887 PteDataMap is the NamedDataMap that will live in the runtime. It is used to give delegates access to opaque named data stored in the PTE file. Open to alternative naming suggestions, maybe 'PTEDataMap' or 'ProgramDataMap'? **Usage** The PteDataMap is owned by the program, and instantiated at program load time if named_data exists in the PTE file. We introduce usage of 'std::optional' here. I think we can also use executorch::aten::optional to avoid adding standard lib ? When initializing delegates, the PteDataMap is given to delegate_init. Delegates can retrieve opaque delegate data by key using 'get_data'. This gives them a FreeableBuffer that they can free later. **Testing** This test uses the C++ flatbuffer API to build a fake program containing named data. We also creates a temp file with sample data that the data loader can wrap around. TODO: e2e test once delegate aot is ready and we can generate a file with named data. **Note** As the PteDataMap wraps around flatbuffer constructs, the Program must outlive the PteDataMap. PteDataMap does not implement - get_metadata; currently, all data stored is opaque. Later, we can implement get_metadata if a backend stores plain tensor data. - load_into; this is mostly used for the training case, and isn't used by delegates, at least not at the moment Differential Revision: [D70213646](https://our.internmc.facebook.com/intern/diff/D70213646/) ghstack-source-id: 269691307
This was referenced Mar 4, 2025
mcr229
reviewed
Mar 4, 2025
…ing" PteDataMap is the NamedDataMap that will live in the runtime. It is used to give delegates access to opaque named data stored in the PTE file. Open to alternative naming suggestions, maybe 'PTEDataMap' or 'ProgramDataMap'? **Usage** The PteDataMap is owned by the program, and instantiated at program load time if named_data exists in the PTE file. We introduce usage of 'std::optional' here. I think we can also use executorch::aten::optional to avoid adding standard lib ? When initializing delegates, the PteDataMap is given to delegate_init. Delegates can retrieve opaque delegate data by key using 'get_data'. This gives them a FreeableBuffer that they can free later. **Testing** This test uses the C++ flatbuffer API to build a fake program containing named data. We also creates a temp file with sample data that the data loader can wrap around. TODO: e2e test once delegate aot is ready and we can generate a file with named data. **Note** As the PteDataMap wraps around flatbuffer constructs, the Program must outlive the PteDataMap. PteDataMap does not implement - get_metadata; currently, all data stored is opaque. Later, we can implement get_metadata if a backend stores plain tensor data. - load_into; this is mostly used for the training case, and isn't used by delegates, at least not at the moment Differential Revision: [D70213646](https://our.internmc.facebook.com/intern/diff/D70213646/) [ghstack-poisoned]
lucylq
added a commit
that referenced
this pull request
Mar 4, 2025
Pull Request resolved: #8887 PteDataMap is the NamedDataMap that will live in the runtime. It is used to give delegates access to opaque named data stored in the PTE file. Open to alternative naming suggestions, maybe 'PTEDataMap' or 'ProgramDataMap'? **Usage** The PteDataMap is owned by the program, and instantiated at program load time if named_data exists in the PTE file. We introduce usage of 'std::optional' here. I think we can also use executorch::aten::optional to avoid adding standard lib ? When initializing delegates, the PteDataMap is given to delegate_init. Delegates can retrieve opaque delegate data by key using 'get_data'. This gives them a FreeableBuffer that they can free later. **Testing** This test uses the C++ flatbuffer API to build a fake program containing named data. We also creates a temp file with sample data that the data loader can wrap around. TODO: e2e test once delegate aot is ready and we can generate a file with named data. **Note** As the PteDataMap wraps around flatbuffer constructs, the Program must outlive the PteDataMap. PteDataMap does not implement - get_metadata; currently, all data stored is opaque. Later, we can implement get_metadata if a backend stores plain tensor data. - load_into; this is mostly used for the training case, and isn't used by delegates, at least not at the moment ghstack-source-id: 269704540 Differential Revision: [D70213646](https://our.internmc.facebook.com/intern/diff/D70213646/)
…ing" PteDataMap is the NamedDataMap that will live in the runtime. It is used to give delegates access to opaque named data stored in the PTE file. Open to alternative naming suggestions, maybe 'PTEDataMap' or 'ProgramDataMap'? **Usage** The PteDataMap is owned by the program, and instantiated at program load time if named_data exists in the PTE file. We introduce usage of 'std::optional' here. I think we can also use executorch::aten::optional to avoid adding standard lib ? When initializing delegates, the PteDataMap is given to delegate_init. Delegates can retrieve opaque delegate data by key using 'get_data'. This gives them a FreeableBuffer that they can free later. **Testing** This test uses the C++ flatbuffer API to build a fake program containing named data. We also creates a temp file with sample data that the data loader can wrap around. TODO: e2e test once delegate aot is ready and we can generate a file with named data. **Note** As the PteDataMap wraps around flatbuffer constructs, the Program must outlive the PteDataMap. PteDataMap does not implement - get_metadata; currently, all data stored is opaque. Later, we can implement get_metadata if a backend stores plain tensor data. - load_into; this is mostly used for the training case, and isn't used by delegates, at least not at the moment Differential Revision: [D70213646](https://our.internmc.facebook.com/intern/diff/D70213646/) [ghstack-poisoned]
lucylq
added a commit
that referenced
this pull request
Mar 4, 2025
Pull Request resolved: #8887 PteDataMap is the NamedDataMap that will live in the runtime. It is used to give delegates access to opaque named data stored in the PTE file. Open to alternative naming suggestions, maybe 'PTEDataMap' or 'ProgramDataMap'? **Usage** The PteDataMap is owned by the program, and instantiated at program load time if named_data exists in the PTE file. We introduce usage of 'std::optional' here. I think we can also use executorch::aten::optional to avoid adding standard lib ? When initializing delegates, the PteDataMap is given to delegate_init. Delegates can retrieve opaque delegate data by key using 'get_data'. This gives them a FreeableBuffer that they can free later. **Testing** This test uses the C++ flatbuffer API to build a fake program containing named data. We also creates a temp file with sample data that the data loader can wrap around. TODO: e2e test once delegate aot is ready and we can generate a file with named data. **Note** As the PteDataMap wraps around flatbuffer constructs, the Program must outlive the PteDataMap. PteDataMap does not implement - get_metadata; currently, all data stored is opaque. Later, we can implement get_metadata if a backend stores plain tensor data. - load_into; this is mostly used for the training case, and isn't used by delegates, at least not at the moment ghstack-source-id: 269716263 Differential Revision: [D70213646](https://our.internmc.facebook.com/intern/diff/D70213646/)
larryliu0820
approved these changes
Mar 5, 2025
…ing" PteDataMap is the NamedDataMap that will live in the runtime. It is used to give delegates access to opaque named data stored in the PTE file. Open to alternative naming suggestions, maybe 'PTEDataMap' or 'ProgramDataMap'? **Usage** The PteDataMap is owned by the program, and instantiated at program load time if named_data exists in the PTE file. We introduce usage of 'std::optional' here. I think we can also use executorch::aten::optional to avoid adding standard lib ? When initializing delegates, the PteDataMap is given to delegate_init. Delegates can retrieve opaque delegate data by key using 'get_data'. This gives them a FreeableBuffer that they can free later. **Testing** This test uses the C++ flatbuffer API to build a fake program containing named data. We also creates a temp file with sample data that the data loader can wrap around. TODO: e2e test once delegate aot is ready and we can generate a file with named data. **Note** As the PteDataMap wraps around flatbuffer constructs, the Program must outlive the PteDataMap. PteDataMap does not implement - get_metadata; currently, all data stored is opaque. Later, we can implement get_metadata if a backend stores plain tensor data. - load_into; this is mostly used for the training case, and isn't used by delegates, at least not at the moment Differential Revision: [D70213646](https://our.internmc.facebook.com/intern/diff/D70213646/) [ghstack-poisoned]
lucylq
added a commit
that referenced
this pull request
Mar 5, 2025
Pull Request resolved: #8887 PteDataMap is the NamedDataMap that will live in the runtime. It is used to give delegates access to opaque named data stored in the PTE file. Open to alternative naming suggestions, maybe 'PTEDataMap' or 'ProgramDataMap'? **Usage** The PteDataMap is owned by the program, and instantiated at program load time if named_data exists in the PTE file. We introduce usage of 'std::optional' here. I think we can also use executorch::aten::optional to avoid adding standard lib ? When initializing delegates, the PteDataMap is given to delegate_init. Delegates can retrieve opaque delegate data by key using 'get_data'. This gives them a FreeableBuffer that they can free later. **Testing** This test uses the C++ flatbuffer API to build a fake program containing named data. We also creates a temp file with sample data that the data loader can wrap around. TODO: e2e test once delegate aot is ready and we can generate a file with named data. **Note** As the PteDataMap wraps around flatbuffer constructs, the Program must outlive the PteDataMap. PteDataMap does not implement - get_metadata; currently, all data stored is opaque. Later, we can implement get_metadata if a backend stores plain tensor data. - load_into; this is mostly used for the training case, and isn't used by delegates, at least not at the moment ghstack-source-id: 269779453 Differential Revision: [D70213646](https://our.internmc.facebook.com/intern/diff/D70213646/)
lucylq
added a commit
that referenced
this pull request
Mar 5, 2025
Pull Request resolved: #8887 PteDataMap is the NamedDataMap that will live in the runtime. It is used to give delegates access to opaque named data stored in the PTE file. Open to alternative naming suggestions, maybe 'PTEDataMap' or 'ProgramDataMap'? **Usage** The PteDataMap is owned by the program, and instantiated at program load time if named_data exists in the PTE file. We introduce usage of 'std::optional' here. I think we can also use executorch::aten::optional to avoid adding standard lib ? When initializing delegates, the PteDataMap is given to delegate_init. Delegates can retrieve opaque delegate data by key using 'get_data'. This gives them a FreeableBuffer that they can free later. **Testing** This test uses the C++ flatbuffer API to build a fake program containing named data. We also creates a temp file with sample data that the data loader can wrap around. TODO: e2e test once delegate aot is ready and we can generate a file with named data. **Note** As the PteDataMap wraps around flatbuffer constructs, the Program must outlive the PteDataMap. PteDataMap does not implement - get_metadata; currently, all data stored is opaque. Later, we can implement get_metadata if a backend stores plain tensor data. - load_into; this is mostly used for the training case, and isn't used by delegates, at least not at the moment ghstack-source-id: 269779453 Differential Revision: [D70213646](https://our.internmc.facebook.com/intern/diff/D70213646/) Co-authored-by: lucylq <[email protected]>
lucylq
added a commit
that referenced
this pull request
Mar 5, 2025
* [executorch][runtime] Introduce PteDataMap for weight sharing Pull Request resolved: #8887 PteDataMap is the NamedDataMap that will live in the runtime. It is used to give delegates access to opaque named data stored in the PTE file. Open to alternative naming suggestions, maybe 'PTEDataMap' or 'ProgramDataMap'? **Usage** The PteDataMap is owned by the program, and instantiated at program load time if named_data exists in the PTE file. We introduce usage of 'std::optional' here. I think we can also use executorch::aten::optional to avoid adding standard lib ? When initializing delegates, the PteDataMap is given to delegate_init. Delegates can retrieve opaque delegate data by key using 'get_data'. This gives them a FreeableBuffer that they can free later. **Testing** This test uses the C++ flatbuffer API to build a fake program containing named data. We also creates a temp file with sample data that the data loader can wrap around. TODO: e2e test once delegate aot is ready and we can generate a file with named data. **Note** As the PteDataMap wraps around flatbuffer constructs, the Program must outlive the PteDataMap. PteDataMap does not implement - get_metadata; currently, all data stored is opaque. Later, we can implement get_metadata if a backend stores plain tensor data. - load_into; this is mostly used for the training case, and isn't used by delegates, at least not at the moment Differential Revision: [D70213646](https://our.internmc.facebook.com/intern/diff/D70213646/) ghstack-source-id: 269691307 * [executorch][runtime] Add get_named_data_map to Program Pull Request resolved: #8853 Add to the program interface, to allow users to retrieve the NDM. Differential Revision: [D70276106](https://our.internmc.facebook.com/intern/diff/D70276106/) ghstack-source-id: 269693108 --------- Co-authored-by: lucylq <[email protected]>
zonglinpeng
pushed a commit
that referenced
this pull request
Mar 6, 2025
Pull Request resolved: #8887 PteDataMap is the NamedDataMap that will live in the runtime. It is used to give delegates access to opaque named data stored in the PTE file. Open to alternative naming suggestions, maybe 'PTEDataMap' or 'ProgramDataMap'? **Usage** The PteDataMap is owned by the program, and instantiated at program load time if named_data exists in the PTE file. We introduce usage of 'std::optional' here. I think we can also use executorch::aten::optional to avoid adding standard lib ? When initializing delegates, the PteDataMap is given to delegate_init. Delegates can retrieve opaque delegate data by key using 'get_data'. This gives them a FreeableBuffer that they can free later. **Testing** This test uses the C++ flatbuffer API to build a fake program containing named data. We also creates a temp file with sample data that the data loader can wrap around. TODO: e2e test once delegate aot is ready and we can generate a file with named data. **Note** As the PteDataMap wraps around flatbuffer constructs, the Program must outlive the PteDataMap. PteDataMap does not implement - get_metadata; currently, all data stored is opaque. Later, we can implement get_metadata if a backend stores plain tensor data. - load_into; this is mostly used for the training case, and isn't used by delegates, at least not at the moment ghstack-source-id: 269779453 Differential Revision: [D70213646](https://our.internmc.facebook.com/intern/diff/D70213646/) Co-authored-by: lucylq <[email protected]>
zonglinpeng
pushed a commit
that referenced
this pull request
Mar 6, 2025
* [executorch][runtime] Introduce PteDataMap for weight sharing Pull Request resolved: #8887 PteDataMap is the NamedDataMap that will live in the runtime. It is used to give delegates access to opaque named data stored in the PTE file. Open to alternative naming suggestions, maybe 'PTEDataMap' or 'ProgramDataMap'? **Usage** The PteDataMap is owned by the program, and instantiated at program load time if named_data exists in the PTE file. We introduce usage of 'std::optional' here. I think we can also use executorch::aten::optional to avoid adding standard lib ? When initializing delegates, the PteDataMap is given to delegate_init. Delegates can retrieve opaque delegate data by key using 'get_data'. This gives them a FreeableBuffer that they can free later. **Testing** This test uses the C++ flatbuffer API to build a fake program containing named data. We also creates a temp file with sample data that the data loader can wrap around. TODO: e2e test once delegate aot is ready and we can generate a file with named data. **Note** As the PteDataMap wraps around flatbuffer constructs, the Program must outlive the PteDataMap. PteDataMap does not implement - get_metadata; currently, all data stored is opaque. Later, we can implement get_metadata if a backend stores plain tensor data. - load_into; this is mostly used for the training case, and isn't used by delegates, at least not at the moment Differential Revision: [D70213646](https://our.internmc.facebook.com/intern/diff/D70213646/) ghstack-source-id: 269691307 * [executorch][runtime] Add get_named_data_map to Program Pull Request resolved: #8853 Add to the program interface, to allow users to retrieve the NDM. Differential Revision: [D70276106](https://our.internmc.facebook.com/intern/diff/D70276106/) ghstack-source-id: 269693108 --------- Co-authored-by: lucylq <[email protected]>
This was referenced Mar 17, 2025
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.
Stack from ghstack (oldest at bottom):
PteDataMap is the NamedDataMap that will live in the runtime. It is used to give delegates access to opaque named data stored in the PTE file. Open to alternative naming suggestions, maybe 'PTEDataMap' or 'ProgramDataMap'?
Usage
The PteDataMap is owned by the program, and instantiated at program load time if named_data exists in the PTE file. We introduce usage of 'std::optional' here. I think we can also use executorch::aten::optional to avoid adding standard lib ?
When initializing delegates, the PteDataMap is given to delegate_init. Delegates can retrieve opaque delegate data by key using 'get_data'. This gives them a FreeableBuffer that they can free later.
Testing
This test uses the C++ flatbuffer API to build a fake program containing named data. We also creates a temp file with sample data that the data loader can wrap around.
TODO: e2e test once delegate aot is ready and we can generate a file with named data.
Note
As the PteDataMap wraps around flatbuffer constructs, the Program must outlive the PteDataMap.
PteDataMap does not implement
Differential Revision: D70213646