Create header for packed weight ops #1072
Merged
Conversation
This file contains 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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/1072
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 452b52b with merge base afc0a02 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D63498956 |
|
Couple of things
|
digantdesai
approved these changes
Oct 14, 2024
metascroy
added a commit
to metascroy/ao
that referenced
this pull request
Oct 15, 2024
Summary: This diff defines a packed_weight hader in torchao/experimental/ops/packed_weights_header.h. The header is 16 bytes and has 4 fields: * format: PackedWeightsFormat (enum) * extra0: int * extra1: int * extra2: int Whenever we have a new format type, we can add a field to the enum. Currently I have a field for the format the universal kernels use, but MPS can have a different format, and KleidiAI also has its own format. I modified the pack ops put this header and the start of the packed weights. When the linear op runs, it reads the header to understand how the weights were packed. Reviewed By: digantdesai Differential Revision: D63498956
metascroy
force-pushed
the
export-D63498956
branch
from
1ba22a5 to
c121875
Compare
|
This pull request was exported from Phabricator. Differential Revision: D63498956 |
Summary: This diff defines a packed_weight hader in torchao/experimental/ops/packed_weights_header.h. The header is 16 bytes and has 4 fields: * format: PackedWeightsFormat (enum) * extra0: int * extra1: int * extra2: int Whenever we have a new format type, we can add a field to the enum. Currently I have a field for the format the universal kernels use, but MPS can have a different format, and KleidiAI also has its own format. I modified the pack ops put this header and the start of the packed weights. When the linear op runs, it reads the header to understand how the weights were packed. Reviewed By: digantdesai Differential Revision: D63498956
metascroy
force-pushed
the
export-D63498956
branch
from
c121875 to
452b52b
Compare
|
This pull request was exported from Phabricator. Differential Revision: D63498956 |
jainapurva
pushed a commit
that referenced
this pull request
Oct 15, 2024
Differential Revision: D63498956 Pull Request resolved: #1072
yanbing-j
pushed a commit
to yanbing-j/ao
that referenced
this pull request
Dec 9, 2024
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:
This diff defines a packed_weight hader in torchao/experimental/ops/packed_weights_header.h.
The header is 16 bytes and has 4 fields:
Whenever we have a new format type, we can add a field to the enum. Currently I have a field for the format the universal kernels use, but MPS can have a different format, and KleidiAI also has its own format.
I modified the pack ops put this header and the start of the packed weights. When the linear op runs, it reads the header to understand how the weights were packed.
Reviewed By: digantdesai
Differential Revision: D63498956