[ET Device Support] Parse device info from serialized tensor in tensor_parser#18328
Merged
Gasoonjia merged 9 commits intogh/gasoonjia/143/basefrom Apr 17, 2026
Merged
[ET Device Support] Parse device info from serialized tensor in tensor_parser#18328Gasoonjia merged 9 commits intogh/gasoonjia/143/basefrom
Gasoonjia merged 9 commits intogh/gasoonjia/143/basefrom
Conversation
…r_parser Parse device info (device_type, device_index) from the serialized ExtraTensorInfo in .pte files into TensorImpl at runtime. When a tensor's extra_tensor_info contains device annotations (e.g., CUDA), the tensor parser now reads and propagates them to the TensorImpl constructor. Tensors without extra_tensor_info default to CPU/0 for backward compatibility with older PTE files.、 Differential Revision: [D97199497](https://our.internmc.facebook.com/intern/diff/D97199497/) [ghstack-poisoned]
Gasoonjia
requested review from
JacobSzwejbka,
kirklandsign,
larryliu0820 and
lucylq
as code owners
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18328
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ✅ You can merge normally! (2 Unrelated Failures)As of commit 6deab13 with merge base 81bc830 ( FLAKY - The following job failed but was likely due to flakiness present on trunk:
BROKEN TRUNK - The following job failed but was 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. |
meta-cla
Bot
added
the
CLA Signed
This was referenced Mar 19, 2026
Merged
This PR needs a
|
…or in tensor_parser" Parse device info (device_type, device_index) from the serialized ExtraTensorInfo in .pte files into TensorImpl at runtime. When a tensor's extra_tensor_info contains device annotations (e.g., CUDA), the tensor parser now reads and propagates them to the TensorImpl constructor. Tensors without extra_tensor_info default to CPU/0 for backward compatibility with older PTE files.、 Differential Revision: [D97199497](https://our.internmc.facebook.com/intern/diff/D97199497/) [ghstack-poisoned]
…or in tensor_parser" Parse device info (device_type, device_index) from the serialized ExtraTensorInfo in .pte files into TensorImpl at runtime. When a tensor's extra_tensor_info contains device annotations (e.g., CUDA), the tensor parser now reads and propagates them to the TensorImpl constructor. Tensors without extra_tensor_info default to CPU/0 for backward compatibility with older PTE files.、 Differential Revision: [D97199497](https://our.internmc.facebook.com/intern/diff/D97199497/) [ghstack-poisoned]
…or in tensor_parser" Parse device info (device_type, device_index) from the serialized ExtraTensorInfo in .pte files into TensorImpl at runtime. When a tensor's extra_tensor_info contains device annotations (e.g., CUDA), the tensor parser now reads and propagates them to the TensorImpl constructor. Tensors without extra_tensor_info default to CPU/0 for backward compatibility with older PTE files.、 Differential Revision: [D97199497](https://our.internmc.facebook.com/intern/diff/D97199497/) [ghstack-poisoned]
This was referenced Mar 24, 2026
lucylq
approved these changes
Mar 31, 2026
…or in tensor_parser" Parse device info (device_type, device_index) from the serialized ExtraTensorInfo in .pte files into TensorImpl at runtime. When a tensor's extra_tensor_info contains device annotations (e.g., CUDA), the tensor parser now reads and propagates them to the TensorImpl constructor. Tensors without extra_tensor_info default to CPU/0 for backward compatibility with older PTE files.、 Differential Revision: [D97199497](https://our.internmc.facebook.com/intern/diff/D97199497/) [ghstack-poisoned]
…or in tensor_parser" Parse device info (device_type, device_index) from the serialized ExtraTensorInfo in .pte files into TensorImpl at runtime. When a tensor's extra_tensor_info contains device annotations (e.g., CUDA), the tensor parser now reads and propagates them to the TensorImpl constructor. Tensors without extra_tensor_info default to CPU/0 for backward compatibility with older PTE files.、 Differential Revision: [D97199497](https://our.internmc.facebook.com/intern/diff/D97199497/) [ghstack-poisoned]
This was referenced Apr 8, 2026
…or in tensor_parser" Parse device info (device_type, device_index) from the serialized ExtraTensorInfo in .pte files into TensorImpl at runtime. When a tensor's extra_tensor_info contains device annotations (e.g., CUDA), the tensor parser now reads and propagates them to the TensorImpl constructor. Tensors without extra_tensor_info default to CPU/0 for backward compatibility with older PTE files.、 Differential Revision: [D97199497](https://our.internmc.facebook.com/intern/diff/D97199497/) [ghstack-poisoned]
Gasoonjia
added a commit
that referenced
this pull request
Apr 13, 2026
…r_parser Pull Request resolved: #18328 Parse device info (device_type, device_index) from the serialized ExtraTensorInfo in .pte files into TensorImpl at runtime. When a tensor's extra_tensor_info contains device annotations (e.g., CUDA), the tensor parser now reads and propagates them to the TensorImpl constructor. Tensors without extra_tensor_info default to CPU/0 for backward compatibility with older PTE files.、 ghstack-source-id: 366667637 @exported-using-ghexport Differential Revision: [D97199497](https://our.internmc.facebook.com/intern/diff/D97199497/)
…or in tensor_parser" Parse device info (device_type, device_index) from the serialized ExtraTensorInfo in .pte files into TensorImpl at runtime. When a tensor's extra_tensor_info contains device annotations (e.g., CUDA), the tensor parser now reads and propagates them to the TensorImpl constructor. Tensors without extra_tensor_info default to CPU/0 for backward compatibility with older PTE files.、 Differential Revision: [D97199497](https://our.internmc.facebook.com/intern/diff/D97199497/) [ghstack-poisoned]
Gasoonjia
added a commit
that referenced
this pull request
Apr 14, 2026
…ensorSpecs (#18078) Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * #18080 * #18328 * #18079 * __->__ #18078 Add end-to-end device type annotation support from export to runtime. Currently we only support one device per graph The overall pipeline is: a. Partitioner use `compile_spec` to determine which device the partitoned blob is runing on b. after lowered partitioned graph to backend, the new-introed propagate_device_pass will annotate the input and output tensors of delegate blob as target device. Differential Revision: [D95842511](https://our.internmc.facebook.com/intern/diff/D95842511/)
Gasoonjia
added a commit
that referenced
this pull request
Apr 14, 2026
…ized Tensor (#18079) Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * #18080 * #18328 * __->__ #18079 * #18078 Propagate device information from `TensorSpec.device` (set by `PropagateDevicePass`) to the serialized `schema.Tensor` in the emitted PTE file, to make runtime further aware of it. Differential Revision: [D95899706](https://our.internmc.facebook.com/intern/diff/D95899706/)
…or in tensor_parser" Parse device info (device_type, device_index) from the serialized ExtraTensorInfo in .pte files into TensorImpl at runtime. When a tensor's extra_tensor_info contains device annotations (e.g., CUDA), the tensor parser now reads and propagates them to the TensorImpl constructor. Tensors without extra_tensor_info default to CPU/0 for backward compatibility with older PTE files.、 Differential Revision: [D97199497](https://our.internmc.facebook.com/intern/diff/D97199497/) [ghstack-poisoned]
Gasoonjia
temporarily deployed
to
cherry-pick-bot
GitHub Actions
Inactive
Gasoonjia
added a commit
that referenced
this pull request
Apr 17, 2026
…r_parser (#18966) This PR was created by the merge bot to help merge the original PR into the main branch. ghstack PR number: #18328 by @Gasoonjia ^ Please use this as the source of truth for the PR details, comments, and reviews ghstack PR base: https://github.com/pytorch/executorch/tree/gh/gasoonjia/143/base ghstack PR head: https://github.com/pytorch/executorch/tree/gh/gasoonjia/143/head Merge bot PR base: https://github.com/pytorch/executorch/tree/main Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/gasoonjia/143/orig Differential Revision: [D97199497](https://our.internmc.facebook.com/intern/diff/D97199497/) @diff-train-skip-merge Co-authored-by: gasoonjia <gasoonjia@icloud.com>
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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):
Parse device info (device_type, device_index) from the serialized ExtraTensorInfo in .pte files into TensorImpl at runtime.
When a tensor's extra_tensor_info contains device annotations (e.g., CUDA), the tensor parser now reads and propagates them to the TensorImpl constructor. Tensors without extra_tensor_info default to CPU/0 for backward compatibility with older PTE files.、
Differential Revision: D97199497