[ET-VK] Implement prepack nodes #6352
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
## Context This diff implements the idea described in the previous diff in this stack. During export, `et_vk.prepack` nodes will be inserted to convert constant tensors to GPU tensor objects. This makes it so that Vulkan operators will not have to account for the possibility that their arguments can potentially be constant tensor data instead of an actual tensor object. Differential Revision: [D64603666](https://our.internmc.facebook.com/intern/diff/D64603666/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/6352
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 480d5a8 with merge base 7493aae ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
SS-JIA
added a commit
that referenced
this pull request
Oct 18, 2024
## Context This diff implements the idea described in the previous diff in this stack. During export, `et_vk.prepack` nodes will be inserted to convert constant tensors to GPU tensor objects. This makes it so that Vulkan operators will not have to account for the possibility that their arguments can potentially be constant tensor data instead of an actual tensor object. Differential Revision: [D64603666](https://our.internmc.facebook.com/intern/diff/D64603666/) ghstack-source-id: 248785585 Pull Request resolved: #6352
|
This pull request was exported from Phabricator. Differential Revision: D64603666 |
jorgep31415
approved these changes
Oct 18, 2024
## Context This diff implements the idea described in the previous diff in this stack. During export, `et_vk.prepack` nodes will be inserted to convert constant tensors to GPU tensor objects. This makes it so that Vulkan operators will not have to account for the possibility that their arguments can potentially be constant tensor data instead of an actual tensor object. Differential Revision: [D64603666](https://our.internmc.facebook.com/intern/diff/D64603666/) [ghstack-poisoned]
SS-JIA
added a commit
that referenced
this pull request
Oct 18, 2024
Pull Request resolved: #6352 ## Context This diff implements the idea described in the previous diff in this stack. During export, `et_vk.prepack` nodes will be inserted to convert constant tensors to GPU tensor objects. This makes it so that Vulkan operators will not have to account for the possibility that their arguments can potentially be constant tensor data instead of an actual tensor object. Differential Revision: [D64603666](https://our.internmc.facebook.com/intern/diff/D64603666/) ghstack-source-id: 248799488
|
This pull request was exported from Phabricator. Differential Revision: D64603666 |
## Context This diff implements the idea described in the previous diff in this stack. During export, `et_vk.prepack` nodes will be inserted to convert constant tensors to GPU tensor objects. This makes it so that Vulkan operators will not have to account for the possibility that their arguments can potentially be constant tensor data instead of an actual tensor object. Differential Revision: [D64603666](https://our.internmc.facebook.com/intern/diff/D64603666/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D64603666 |
SS-JIA
added a commit
that referenced
this pull request
Oct 18, 2024
Pull Request resolved: #6352 ## Context This diff implements the idea described in the previous diff in this stack. During export, `et_vk.prepack` nodes will be inserted to convert constant tensors to GPU tensor objects. This makes it so that Vulkan operators will not have to account for the possibility that their arguments can potentially be constant tensor data instead of an actual tensor object. ghstack-source-id: 248824926 Differential Revision: [D64603666](https://our.internmc.facebook.com/intern/diff/D64603666/)
## Context This diff implements the idea described in the previous diff in this stack. During export, `et_vk.prepack` nodes will be inserted to convert constant tensors to GPU tensor objects. This makes it so that Vulkan operators will not have to account for the possibility that their arguments can potentially be constant tensor data instead of an actual tensor object. Differential Revision: [D64603666](https://our.internmc.facebook.com/intern/diff/D64603666/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D64603666 |
SS-JIA
added a commit
that referenced
this pull request
Oct 18, 2024
Pull Request resolved: #6352 ## Context This diff implements the idea described in the previous diff in this stack. During export, `et_vk.prepack` nodes will be inserted to convert constant tensors to GPU tensor objects. This makes it so that Vulkan operators will not have to account for the possibility that their arguments can potentially be constant tensor data instead of an actual tensor object. ghstack-source-id: 248830017 Differential Revision: [D64603666](https://our.internmc.facebook.com/intern/diff/D64603666/)
## Context This diff implements the idea described in the previous diff in this stack. During export, `et_vk.prepack` nodes will be inserted to convert constant tensors to GPU tensor objects. This makes it so that Vulkan operators will not have to account for the possibility that their arguments can potentially be constant tensor data instead of an actual tensor object. Differential Revision: [D64603666](https://our.internmc.facebook.com/intern/diff/D64603666/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D64603666 |
SS-JIA
added a commit
that referenced
this pull request
Oct 18, 2024
Pull Request resolved: #6352 ## Context This diff implements the idea described in the previous diff in this stack. During export, `et_vk.prepack` nodes will be inserted to convert constant tensors to GPU tensor objects. This makes it so that Vulkan operators will not have to account for the possibility that their arguments can potentially be constant tensor data instead of an actual tensor object. ghstack-source-id: 248867364 Differential Revision: [D64603666](https://our.internmc.facebook.com/intern/diff/D64603666/)
facebook-github-bot
temporarily deployed
to
cherry-pick-bot
GitHub Actions
Inactive
|
This pull request has been merged in 339bb74. |
SS-JIA
added a commit
that referenced
this pull request
Apr 24, 2025
…of constant tensors ## Context Refer to #6352 for why the `insert_prepack_nodes` pass is needed. The current logic of the pass assumes that each constant tensor node has only one use. However, in reality, a constant tensor node may have multiple uses; some of which may require the insertion of a prepacking node and some which may not (since they may choose to apply some special packing in the operator implementation). Currently, if any uses of a constant tensor node handles its own prepacking, then prepacking nodes will not be inserted. This makes it so that a model will produce a type error during runtime when an operator receives a `TensorRef` but expects a `Tensor`. ## Changes Improve the logic of the pass to handle constant tensor nodes which have multiple uses. If any use does not handle its own prepacking, then a prepacking node will be inserted for those usages. Differential Revision: [D73592619](https://our.internmc.facebook.com/intern/diff/D73592619/) [ghstack-poisoned]
SS-JIA
added a commit
that referenced
this pull request
Apr 24, 2025
…of constant tensors ## Context Refer to #6352 for why the `insert_prepack_nodes` pass is needed. The current logic of the pass assumes that each constant tensor node has only one use. However, in reality, a constant tensor node may have multiple uses; some of which may require the insertion of a prepacking node and some which may not (since they may choose to apply some special packing in the operator implementation). Currently, if any uses of a constant tensor node handles its own prepacking, then prepacking nodes will not be inserted. This makes it so that a model will produce a type error during runtime when an operator receives a `TensorRef` but expects a `Tensor`. ## Changes Improve the logic of the pass to handle constant tensor nodes which have multiple uses. If any use does not handle its own prepacking, then a prepacking node will be inserted for those usages. Differential Revision: [D73592619](https://our.internmc.facebook.com/intern/diff/D73592619/) ghstack-source-id: 280054012 Pull Request resolved: #10426
SS-JIA
pushed a commit
that referenced
this pull request
Apr 25, 2025
…of constant tensors (#10488) ## Context Refer to #6352 for why the `insert_prepack_nodes` pass is needed. The current logic of the pass assumes that each constant tensor node has only one use. However, in reality, a constant tensor node may have multiple uses; some of which may require the insertion of a prepacking node and some which may not (since they may choose to apply some special packing in the operator implementation). Currently, if any uses of a constant tensor node handles its own prepacking, then prepacking nodes will not be inserted. This makes it so that a model will produce a type error during runtime when an operator receives a `TensorRef` but expects a `Tensor`. ## Changes Improve the logic of the pass to handle constant tensor nodes which have multiple uses. If any use does not handle its own prepacking, then a prepacking node will be inserted for those usages. Differential Revision: [D73592619](https://our.internmc.facebook.com/intern/diff/D73592619/)
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):
Context
This diff implements the idea described in the previous diff in this stack. During export,
et_vk.prepacknodes will be inserted to convert constant tensors to GPU tensor objects. This makes it so that Vulkan operators will not have to account for the possibility that their arguments can potentially be constant tensor data instead of an actual tensor object.Differential Revision: D64603666