[wip] Merge ndm and pte_data_map #11579
Closed
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
Merge ndm and pte data map to enable cases like lora, where we introduce - shared weights in the pte file (this is true of any xnnpack pte file, as weights are placed in shared space by default now). - shared weights in external file Pass the merged data map into method, so it can access both. Note: have to remove the const qualifiers, as the flat tensor data map is modified. Differential Revision: [D76447708](https://our.internmc.facebook.com/intern/diff/D76447708/) [ghstack-poisoned]
lucylq
requested review from
cccclai,
JacobSzwejbka,
swolchok and
larryliu0820
as code owners
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11579
Note: Links to docs will display an error until the docs builds have been completed. ❌ 3 New FailuresAs of commit bb1695c with merge base c4c4763 ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
lucylq
added a commit
that referenced
this pull request
Jun 11, 2025
Merge ndm and pte data map to enable cases like lora, where we introduce - shared weights in the pte file (this is true of any xnnpack pte file, as weights are placed in shared space by default now). - shared weights in external file Pass the merged data map into method, so it can access both. Note: have to remove the const qualifiers, as the flat tensor data map is modified. Differential Revision: [D76447708](https://our.internmc.facebook.com/intern/diff/D76447708/) ghstack-source-id: 289741480 Pull Request resolved: #11579
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D76447708 |
This PR needs a
|
Merge ndm and pte data map to enable cases like lora, where we introduce - shared weights in the pte file (this is true of any xnnpack pte file, as weights are placed in shared space by default now). - shared weights in external file Pass the merged data map into method, so it can access both. Note: have to remove the const qualifiers, as the flat tensor data map is modified. Differential Revision: [D76447708](https://our.internmc.facebook.com/intern/diff/D76447708/) [ghstack-poisoned]
lucylq
added a commit
that referenced
this pull request
Jun 12, 2025
Pull Request resolved: #11579 Merge ndm and pte data map to enable cases like lora, where we introduce - shared weights in the pte file (this is true of any xnnpack pte file, as weights are placed in shared space by default now). - shared weights in external file Pass the merged data map into method, so it can access both. Note: removing const qualifiers, as the flat tensor data map can potentially be modified now. Differential Revision: [D76447708](https://our.internmc.facebook.com/intern/diff/D76447708/) ghstack-source-id: 289855981
|
This pull request was exported from Phabricator. Differential Revision: D76447708 |
Merge ndm and pte data map to enable cases like lora, where we introduce - shared weights in the pte file (this is true of any xnnpack pte file, as weights are placed in shared space by default now). - shared weights in external file Pass the merged data map into method, so it can access both. Note: have to remove the const qualifiers, as the flat tensor data map is modified. Differential Revision: [D76447708](https://our.internmc.facebook.com/intern/diff/D76447708/) [ghstack-poisoned]
lucylq
added a commit
that referenced
this pull request
Jun 12, 2025
Pull Request resolved: #11579 Merge ndm and pte data map to enable cases like lora, where we introduce - shared weights in the pte file (this is true of any xnnpack pte file, as weights are placed in shared space by default now). - shared weights in external file Pass the merged data map into method, so it can access both. Note: removing const qualifiers, as the flat tensor data map can potentially be modified now. ghstack-source-id: 289886680 Differential Revision: [D76447708](https://our.internmc.facebook.com/intern/diff/D76447708/)
|
This pull request was exported from Phabricator. Differential Revision: D76447708 |
Merge ndm and pte data map to enable cases like lora, where we introduce - shared weights in the pte file (this is true of any xnnpack pte file, as weights are placed in shared space by default now). - shared weights in external file Pass the merged data map into method, so it can access both. Note: have to remove the const qualifiers, as the flat tensor data map is modified. Differential Revision: [D76447708](https://our.internmc.facebook.com/intern/diff/D76447708/) [ghstack-poisoned]
lucylq
added a commit
that referenced
this pull request
Jun 12, 2025
Pull Request resolved: #11579 Merge ndm and pte data map to enable cases like lora, where we introduce - shared weights in the pte file (this is true of any xnnpack pte file, as weights are placed in shared space by default now). - shared weights in external file Pass the merged data map into method, so it can access both. Note: removing const qualifiers, as the flat tensor data map can potentially be modified now. ghstack-source-id: 289887980 Differential Revision: [D76447708](https://our.internmc.facebook.com/intern/diff/D76447708/)
|
This pull request was exported from Phabricator. Differential Revision: D76447708 |
lucylq
had a problem deploying
to
cherry-pick-bot
GitHub Actions
Failure
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):
Merge ndm and pte data map to enable cases like lora, where we introduce
Pass the merged data map into method, so it can access both.
Note: have to remove the const qualifiers, as the flat tensor data map is modified.
Differential Revision: D76447708