always partition used static attr #354
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
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D49129705 |
|
This pull request was exported from Phabricator. Differential Revision: D49129705 |
mcr229
force-pushed
the
export-D49129705
branch
from
5d6be47 to
1e1c4fe
Compare
|
This pull request was exported from Phabricator. Differential Revision: D49129705 |
mcr229
force-pushed
the
export-D49129705
branch
from
1e1c4fe to
7234f3b
Compare
Differential Revision: D49068312 fbshipit-source-id: 17a37a8089e5b685aeed0357fb9f8aa2618deb82
Differential Revision: D49301134 fbshipit-source-id: f6b03ff071f9c366f6de9fe3f8e6af1579d69fb6
Differential Revision: D49129704 fbshipit-source-id: 9ef62a2e11b8616b8d0324607112261511837fb6
Summary: Pull Request resolved: pytorch/executorch#354 This is to enable lowering ViT Model. ViT's Multiheadattention is decomposed to many linears. addmm is not delegateable if it is not derived from torch.nn.linear. There are some addmms in ViT which are derived from MultiHeadAttention. As a result to improve performance we need to partition addmms in the operator list rather than by module. These changes are merged from: D49129703 as both changes are required to keep OD tests working For supported_operators that use static data, the data should always be partitioned along with that operator. This is required for adding addmm into supported_operator set because it allows us to partition in the weight and bias data. Differential Revision: D49129705 fbshipit-source-id: 57789f3249cb626c18f313bc86d85d85bb826cfe
|
This pull request was exported from Phabricator. Differential Revision: D49129705 |
mcr229
force-pushed
the
export-D49129705
branch
from
7234f3b to
9a71de1
Compare
|
This pull request has been merged in 60ea5c6. |
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.
Summary: For supported_operators that use static data, the data should always be partitioned along with that operator. This is required for adding addmm into supported_operator set because it allows us to partition in the weight and bias data.
Differential Revision: D49129705