Increase code reuse between FP32, FP16, INT8, INT4 embedding types for infer TBE #833
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
|
This pull request was exported from Phabricator. Differential Revision: D33343450 |
1 similar comment
|
This pull request was exported from Phabricator. Differential Revision: D33343450 |
jianyuh
added a commit
to jianyuh/FBGEMM
that referenced
this pull request
Dec 29, 2021
…r infer TBE (pytorch#833) Summary: Pull Request resolved: pytorch#833 We merge the implementation for {FP32, FP16, INT8, INT4} weights in inference TBE into one unified template and increase the code reuse between these implementations. This will pave the way for the future enhancements (no need to change all 4 implementations for one new feature). Differential Revision: D33343450 fbshipit-source-id: f676636b3895412e9401058d77065c8122c1e853
jianyuh
force-pushed
the
export-D33343450
branch
from
6788871 to
9a215a4
Compare
jianyuh
added a commit
to jianyuh/FBGEMM
that referenced
this pull request
Dec 29, 2021
…r infer TBE (pytorch#833) Summary: Pull Request resolved: pytorch#833 We merge the implementation for {FP32, FP16, INT8, INT4} weights in inference TBE into one unified template and increase the code reuse between these implementations. This will pave the way for the future enhancements (no need to change all 4 implementations for one new feature). Differential Revision: D33343450 fbshipit-source-id: 059d08b0f05437fff275687692552649d2354058
jianyuh
force-pushed
the
export-D33343450
branch
from
9a215a4 to
bf5ca7d
Compare
|
This pull request was exported from Phabricator. Differential Revision: D33343450 |
jianyuh
added a commit
to jianyuh/FBGEMM
that referenced
this pull request
Dec 29, 2021
…r infer TBE (pytorch#833) Summary: Pull Request resolved: pytorch#833 We merge the implementation for {FP32, FP16, INT8, INT4} weights in inference TBE into one unified template and increase the code reuse between these implementations. This will pave the way for the future enhancements (no need to change all 4 implementations for one new feature). Reviewed By: rweyrauch Differential Revision: D33343450 fbshipit-source-id: 3765be6c2024e3f7a74f6c1b92cb82194e3bf5eb
|
This pull request was exported from Phabricator. Differential Revision: D33343450 |
jianyuh
force-pushed
the
export-D33343450
branch
from
bf5ca7d to
372b4f2
Compare
jianyuh
added a commit
to jianyuh/FBGEMM
that referenced
this pull request
Dec 29, 2021
…r infer TBE (pytorch#833) Summary: Pull Request resolved: pytorch#833 We merge the implementation for {FP32, FP16, INT8, INT4} weights in inference TBE into one unified template and increase the code reuse between these implementations. This will pave the way for the future enhancements (no need to change all 4 implementations for one new feature). Reviewed By: rweyrauch Differential Revision: D33343450 fbshipit-source-id: d1c8be3b6cdfca809828f19dd87d4d2744f9111f
jianyuh
force-pushed
the
export-D33343450
branch
from
372b4f2 to
3d7b04e
Compare
|
This pull request was exported from Phabricator. Differential Revision: D33343450 |
jianyuh
added a commit
to jianyuh/FBGEMM
that referenced
this pull request
Dec 29, 2021
…r infer TBE (pytorch#833) Summary: Pull Request resolved: pytorch#833 We merge the implementation for {FP32, FP16, INT8, INT4} weights in inference TBE into one unified template and increase the code reuse between these implementations. This will pave the way for the future enhancements (no need to change all 4 implementations for one new feature). Reviewed By: rweyrauch Differential Revision: D33343450 fbshipit-source-id: 9b54359e1126a1c8cf31bcc50daaefbbcb00ead1
jianyuh
force-pushed
the
export-D33343450
branch
from
3d7b04e to
de6e02e
Compare
|
This pull request was exported from Phabricator. Differential Revision: D33343450 |
jianyuh
added a commit
to jianyuh/FBGEMM
that referenced
this pull request
Dec 29, 2021
…r infer TBE (pytorch#833) Summary: Pull Request resolved: pytorch#833 We merge the implementation for {FP32, FP16, INT8, INT4} weights in inference TBE into one unified template and increase the code reuse between these implementations. This will pave the way for the future enhancements (no need to change all 4 implementations for one new feature). Reviewed By: rweyrauch Differential Revision: D33343450 fbshipit-source-id: 9eb432dae1a5bb0ec33b8be5088ebe85d08f236c
jianyuh
force-pushed
the
export-D33343450
branch
from
de6e02e to
3d89ccd
Compare
|
This pull request was exported from Phabricator. Differential Revision: D33343450 |
jianyuh
added a commit
to jianyuh/FBGEMM
that referenced
this pull request
Dec 30, 2021
…r infer TBE (pytorch#833) Summary: Pull Request resolved: pytorch#833 We merge the implementation for {FP32, FP16, INT8, INT4} weights in inference TBE into one unified template and increase the code reuse between these implementations. This will pave the way for the future enhancements (no need to change all 4 implementations for one new feature). Reviewed By: rweyrauch Differential Revision: D33343450 fbshipit-source-id: 92ae814798b82a47cf6e301932f7949a334ab864
|
This pull request was exported from Phabricator. Differential Revision: D33343450 |
jianyuh
force-pushed
the
export-D33343450
branch
from
3d89ccd to
535ab71
Compare
…r infer TBE (pytorch#833) Summary: Pull Request resolved: pytorch#833 We merge the implementation for {FP32, FP16, INT8, INT4} weights in inference TBE into one unified template and increase the code reuse between these implementations. This will pave the way for the future enhancements (no need to change all 4 implementations for one new feature). Reviewed By: rweyrauch Differential Revision: D33343450 fbshipit-source-id: 830d5039b8262b44d96da6b8192d628dd0a1f4a7
jianyuh
force-pushed
the
export-D33343450
branch
from
535ab71 to
6bde65d
Compare
|
This pull request was exported from Phabricator. Differential Revision: D33343450 |
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: We merge the implementation for {FP32, FP16, INT8, INT4} weights in inference TBE into one unified template and increase the code reuse between these implementations. This will pave the way for the future enhancements (no need to change all 4 implementations for one new feature).
Differential Revision: D33343450