Fix quantized linear -> quantized fully connected replacement pass + add quantized fully connected per_tensor #6976
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/6976
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 75f1476 with merge base cd306d3 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D66208417 |
Contributor
Author
|
@pytorchbot label "topic: not user facing" |
facebook-github-bot
pushed a commit
that referenced
this pull request
Nov 25, 2024
…add quantized fully connected per_tensor (#6976) Summary: As titled. This allows removing the outer loop unrolling in cases where the input to linear is a vector. Shaves 8.5k cyles from WW stage 1 model. Differential Revision: D66208417
facebook-github-bot
force-pushed
the
export-D66208417
branch
from
b0eb57f to
c04e166
Compare
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D66208417 |
mcremon-meta
added a commit
that referenced
this pull request
Nov 25, 2024
…add quantized fully connected per_tensor (#6976) Summary: As titled. This allows removing the outer loop unrolling in cases where the input to linear is a vector. Shaves 8.5k cyles from WW stage 1 model. Differential Revision: D66208417
mcremon-meta
force-pushed
the
export-D66208417
branch
from
c04e166 to
42003c3
Compare
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D66208417 |
mcremon-meta
added a commit
that referenced
this pull request
Nov 27, 2024
…add quantized fully connected per_tensor (#6976) Summary: As titled. This allows removing the outer loop unrolling in cases where the input to linear is a vector. Shaves 8.5k cyles from WW stage 1 model. Differential Revision: D66208417
mcremon-meta
force-pushed
the
export-D66208417
branch
from
42003c3 to
93a02cc
Compare
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D66208417 |
mcremon-meta
added a commit
that referenced
this pull request
Dec 1, 2024
…add quantized fully connected per_tensor (#6976) Summary: As titled. This allows removing the outer loop unrolling in cases where the input to linear is a vector. Shaves 8.5k cyles from WW stage 1 model. Differential Revision: D66208417
mcremon-meta
force-pushed
the
export-D66208417
branch
from
93a02cc to
c9992eb
Compare
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D66208417 |
facebook-github-bot
pushed a commit
that referenced
this pull request
Dec 3, 2024
…add quantized fully connected per_tensor (#6976) Summary: As titled. This allows removing the outer loop unrolling in cases where the input to linear is a vector. Shaves 8.5k cyles from WW stage 1 model. Differential Revision: D66208417
facebook-github-bot
force-pushed
the
export-D66208417
branch
from
c9992eb to
3829c66
Compare
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D66208417 |
zonglinpeng
approved these changes
Dec 3, 2024
Contributor
|
unrelated lint error, please rebase and try |
mcremon-meta
added a commit
that referenced
this pull request
Dec 4, 2024
…add quantized fully connected per_tensor (#6976) Summary: As titled. This allows removing the outer loop unrolling in cases where the input to linear is a vector. Shaves 8.5k cyles from WW stage 1 model. Reviewed By: zonglinpeng Differential Revision: D66208417
mcremon-meta
force-pushed
the
export-D66208417
branch
from
3829c66 to
27f0b82
Compare
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D66208417 |
facebook-github-bot
force-pushed
the
export-D66208417
branch
from
27f0b82 to
b951ccf
Compare
facebook-github-bot
pushed a commit
that referenced
this pull request
Dec 4, 2024
…add quantized fully connected per_tensor (#6976) Summary: As titled. This allows removing the outer loop unrolling in cases where the input to linear is a vector. Shaves 8.5k cyles from WW stage 1 model. Reviewed By: zonglinpeng Differential Revision: D66208417
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D66208417 |
mcremon-meta
added a commit
that referenced
this pull request
Dec 4, 2024
…add quantized fully connected per_tensor (#6976) Summary: As titled. This allows removing the outer loop unrolling in cases where the input to linear is a vector. Shaves 8.5k cyles from WW stage 1 model. Reviewed By: zonglinpeng Differential Revision: D66208417
mcremon-meta
force-pushed
the
export-D66208417
branch
from
b951ccf to
3c8360f
Compare
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D66208417 |
…add quantized fully connected per_tensor (#6976) Summary: As titled. This allows removing the outer loop unrolling in cases where the input to linear is a vector. Shaves 8.5k cyles from WW stage 1 model. Reviewed By: zonglinpeng Differential Revision: D66208417
facebook-github-bot
force-pushed
the
export-D66208417
branch
from
3c8360f to
75f1476
Compare
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D66208417 |
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:
As titled. This allows removing the outer loop unrolling in cases where the input to linear is a vector.
Shaves ~10k cyles from WW stage 1 model.
Differential Revision: D66208417