Refactor attention v2 #10707
Merged
Refactor attention v2 #10707
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
Pull Request resolved: #10623 Pull attention creation out of Transformer/TransformerBlock. Instead, pass the layers into Transformer. The motivation is to customize linear layers in attention for LoRA (eg. make wq into a LoraLinear instead of a regular linear). In the next diff (D73517350), we pull wq,wk,wv,wo out of the attention and pass those in as well. This allows us to customize attention parameters without passing in ModelArgs and doing the customization deep inside attention.py. I think this modularizes our attention/transformer components, though also means that users have to do some more work to construct the attention layers and pass it to transformer. It follows the torchtune structure more closely, eg. https://github.com/pytorch/torchtune/blob/main/torchtune/models/llama3_2/_component_builders.py#L221 Previously here: D73474110 ghstack-source-id: 282118266 @exported-using-ghexport Differential Revision: [D73538697](https://our.internmc.facebook.com/intern/diff/D73538697/)
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/10707
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: ❌ 1 New FailureAs of commit 7e997a4 with merge base 4129ebe ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
kirklandsign
approved these changes
May 6, 2025
phaiting
pushed a commit
that referenced
this pull request
May 6, 2025
Pull Request resolved: #10623 Pull attention creation out of Transformer/TransformerBlock. Instead, pass the layers into Transformer. The motivation is to customize linear layers in attention for LoRA (eg. make wq into a LoraLinear instead of a regular linear). In the next diff (D73517350), we pull wq,wk,wv,wo out of the attention and pass those in as well. This allows us to customize attention parameters without passing in ModelArgs and doing the customization deep inside attention.py. I think this modularizes our attention/transformer components, though also means that users have to do some more work to construct the attention layers and pass it to transformer. It follows the torchtune structure more closely, eg. https://github.com/pytorch/torchtune/blob/main/torchtune/models/llama3_2/_component_builders.py#L221 Previously here: D73474110 ghstack-source-id: 282118266 @exported-using-ghexport Differential Revision: [D73538697](https://our.internmc.facebook.com/intern/diff/D73538697/)
jhelsby
pushed a commit
to jhelsby/executorch
that referenced
this pull request
May 9, 2025
Pull Request resolved: pytorch#10623 Pull attention creation out of Transformer/TransformerBlock. Instead, pass the layers into Transformer. The motivation is to customize linear layers in attention for LoRA (eg. make wq into a LoraLinear instead of a regular linear). In the next diff (D73517350), we pull wq,wk,wv,wo out of the attention and pass those in as well. This allows us to customize attention parameters without passing in ModelArgs and doing the customization deep inside attention.py. I think this modularizes our attention/transformer components, though also means that users have to do some more work to construct the attention layers and pass it to transformer. It follows the torchtune structure more closely, eg. https://github.com/pytorch/torchtune/blob/main/torchtune/models/llama3_2/_component_builders.py#L221 Previously here: D73474110 ghstack-source-id: 282118266 @exported-using-ghexport Differential Revision: [D73538697](https://our.internmc.facebook.com/intern/diff/D73538697/)
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.
This PR was created by the merge bot to help merge the original PR into the main branch.
ghstack PR number: #10623 by @lucylq
^ 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/lucylq/74/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/lucylq/74/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/main
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/lucylq/74/orig
@diff-train-skip-merge