[ET-VK] Runtime support for NamedDataMap #13498
Merged
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
added 2 commits
August 18, 2025 10:28
…elines()` to `prepare()` Title says it all; `prepare()` is a more appropriate place for this action than `prepare_pipelines()`. ## Motivation Fix potential floating point exception (divide-by-zero) during tests. Some tests don't call `prepare_pipelines()`, which means `execute_threshold_node_count_` is unititialized, causing a divide by zero in execute when trying to modulo with `execute_threshold_node_count_` Differential Revision: [D80468138](https://our.internmc.facebook.com/intern/diff/D80468138/) ghstack-source-id: 303779589 Pull Request resolved: #13478
Pull Request resolved: #13472 Allow VulkanBackend to load constant tensors from the NamedDataMap instead of the constant data section of the delegate blob. ## Motivation This enables several key results: * Unblocks delegate retargetability with other backends * Allows reducing peak memory usage when loading models by freeing constant weight data as it gets moved to the GPU ## Changes * Allow `TensorRef` to be constructed with a `FreeableBuffer` rvalue * Add ability to load constant data from `NamedDataMap` in `VulkanBackend.cpp` * When prepacking, free the constant data pointer once it's been copied to the staging buffer ghstack-source-id: 303830113 Differential Revision: [D80460035](https://our.internmc.facebook.com/intern/diff/D80460035/)
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/13498
Note: Links to docs will display an error until the docs builds have been completed. ⏳ 9 Pending, 1 Unrelated FailureAs of commit 5b3585c with merge base 5ff0208 ( 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. |
meta-cla
bot
added
the
CLA Signed
SS-JIA
approved these changes
Aug 19, 2025
agrima1304
pushed a commit
to agrima1304/executorch
that referenced
this pull request
Aug 26, 2025
Summary: Allow VulkanBackend to load constant tensors from the NamedDataMap instead of the constant data section of the delegate blob. ## Motivation This enables several key results: * Unblocks delegate retargetability with other backends * Allows reducing peak memory usage when loading models by freeing constant weight data as it gets moved to the GPU ## Changes * Allow `TensorRef` to be constructed with a `FreeableBuffer` rvalue * Add ability to load constant data from `NamedDataMap` in `VulkanBackend.cpp` * When prepacking, free the constant data pointer once it's been copied to the staging buffer Test Plan: CI Validate results by collecting memory measurements in the next few diffs. Differential Revision: [D80460035](https://our.internmc.facebook.com/intern/diff/D80460035) [ghstack-poisoned]
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.
This PR was created by the merge bot to help merge the original PR into the main branch.
ghstack PR number: #13472 by @SS-JIA
^ 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/SS-JIA/290/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/SS-JIA/290/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/SS-JIA/293/orig
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/SS-JIA/290/orig
@diff-train-skip-merge