Support min/max carry over for eager mode from_float method #2046
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
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D57747749 |
kwanghoon-meta
added a commit
to kwanghoon-meta/torchrec
that referenced
this pull request
May 28, 2024
…2046) Summary: X-link: pytorch/pytorch#127309 After QAT is completed or given pre-tuned weight observer via tunable PTQ algorithm, it should not over-write again with a given weight, at least for static QAT never. Dynamic QAT also does not require to re-run weight observer again by design. This is a fix Differential Revision: D57747749
kwanghoon-meta
force-pushed
the
export-D57747749
branch
from
097ede5 to
3ae2a51
Compare
|
This pull request was exported from Phabricator. Differential Revision: D57747749 |
kwanghoon-meta
added a commit
to kwanghoon-meta/torchrec
that referenced
this pull request
May 28, 2024
…2046) Summary: X-link: pytorch/pytorch#127309 After QAT is completed or given pre-tuned weight observer via tunable PTQ algorithm, it should not over-write again with a given weight, at least for static QAT never. Dynamic QAT also does not require to re-run weight observer again by design. This is a fix Differential Revision: D57747749
kwanghoon-meta
force-pushed
the
export-D57747749
branch
from
3ae2a51 to
061c63c
Compare
|
This pull request was exported from Phabricator. Differential Revision: D57747749 |
kwanghoon-meta
added a commit
to kwanghoon-meta/torchrec
that referenced
this pull request
May 28, 2024
…2046) Summary: X-link: pytorch/pytorch#127309 After QAT is completed or given pre-tuned weight observer via tunable PTQ algorithm, it should not over-write again with a given weight, at least for static QAT never. Dynamic QAT also does not require to re-run weight observer again by design. This is a fix Differential Revision: D57747749
kwanghoon-meta
force-pushed
the
export-D57747749
branch
from
061c63c to
b903c5e
Compare
|
This pull request was exported from Phabricator. Differential Revision: D57747749 |
kwanghoon-meta
force-pushed
the
export-D57747749
branch
from
b903c5e to
cb1d111
Compare
kwanghoon-meta
added a commit
to kwanghoon-meta/torchrec
that referenced
this pull request
May 28, 2024
…2046) Summary: X-link: pytorch/pytorch#127309 After QAT is completed or given pre-tuned weight observer via tunable PTQ algorithm, it should not over-write again with a given weight, at least for static QAT never. Dynamic QAT also does not require to re-run weight observer again by design. This is a fix Differential Revision: D57747749
|
This pull request was exported from Phabricator. Differential Revision: D57747749 |
kwanghoon-meta
added a commit
to kwanghoon-meta/torchrec
that referenced
this pull request
May 28, 2024
…2046) Summary: X-link: pytorch/pytorch#127309 After QAT is completed or given pre-tuned weight observer via tunable PTQ algorithm, it should not over-write again with a given weight, at least for static QAT never. Dynamic QAT also does not require to re-run weight observer again by design. This is a fix Differential Revision: D57747749
kwanghoon-meta
force-pushed
the
export-D57747749
branch
from
cb1d111 to
94981e4
Compare
|
This pull request was exported from Phabricator. Differential Revision: D57747749 |
kwanghoon-meta
added a commit
to kwanghoon-meta/torchrec
that referenced
this pull request
May 28, 2024
…2046) Summary: X-link: pytorch/pytorch#127309 After QAT is completed or given pre-tuned weight observer via tunable PTQ algorithm, it should not over-write again with a given weight, at least for static QAT never. Dynamic QAT also does not require to re-run weight observer again by design. This is a fix Differential Revision: D57747749
kwanghoon-meta
force-pushed
the
export-D57747749
branch
from
94981e4 to
1b7d2b4
Compare
|
This pull request was exported from Phabricator. Differential Revision: D57747749 |
kwanghoon-meta
added a commit
to kwanghoon-meta/torchrec
that referenced
this pull request
May 28, 2024
…2046) Summary: X-link: pytorch/pytorch#127309 After QAT is completed or given pre-tuned weight observer via tunable PTQ algorithm, it should not over-write again with a given weight, at least for static QAT never. Dynamic QAT also does not require to re-run weight observer again by design. This is a fix Differential Revision: D57747749
kwanghoon-meta
force-pushed
the
export-D57747749
branch
from
1b7d2b4 to
266dc95
Compare
|
This pull request was exported from Phabricator. Differential Revision: D57747749 |
kwanghoon-meta
added a commit
to kwanghoon-meta/torchrec
that referenced
this pull request
May 29, 2024
…2046) Summary: X-link: pytorch/pytorch#127309 After QAT is completed or given pre-tuned weight observer via tunable PTQ algorithm, it should not over-write again with a given weight, at least for static QAT never. Dynamic QAT also does not require to re-run weight observer again by design. This is a fix Reviewed By: jerryzh168 Differential Revision: D57747749
kwanghoon-meta
force-pushed
the
export-D57747749
branch
from
0b88062 to
b0c946b
Compare
|
This pull request was exported from Phabricator. Differential Revision: D57747749 |
kwanghoon-meta
force-pushed
the
export-D57747749
branch
from
b0c946b to
f78d62d
Compare
kwanghoon-meta
added a commit
to kwanghoon-meta/torchrec
that referenced
this pull request
May 29, 2024
…2046) Summary: X-link: pytorch/pytorch#127309 After QAT is completed or given pre-tuned weight observer via tunable PTQ algorithm, it should not over-write again with a given weight, at least for static QAT never. Dynamic QAT also does not require to re-run weight observer again by design. This is a fix Reviewed By: jerryzh168 Differential Revision: D57747749
|
This pull request was exported from Phabricator. Differential Revision: D57747749 |
kwanghoon-meta
added a commit
to kwanghoon-meta/torchrec
that referenced
this pull request
May 29, 2024
…2046) Summary: X-link: pytorch/pytorch#127309 After QAT is completed or given pre-tuned weight observer via tunable PTQ algorithm, it should not over-write again with a given weight, at least for static QAT never. Dynamic QAT also does not require to re-run weight observer again by design. This is a fix Reviewed By: jerryzh168 Differential Revision: D57747749
kwanghoon-meta
force-pushed
the
export-D57747749
branch
from
f78d62d to
cafccb8
Compare
|
This pull request was exported from Phabricator. Differential Revision: D57747749 |
…2046) Summary: X-link: pytorch/pytorch#127309 After QAT is completed or given pre-tuned weight observer via tunable PTQ algorithm, it should not over-write again with a given weight, at least for static QAT never. Dynamic QAT also does not require to re-run weight observer again by design. This is a fix Reviewed By: jerryzh168 Differential Revision: D57747749
kwanghoon-meta
force-pushed
the
export-D57747749
branch
from
cafccb8 to
156a851
Compare
kwanghoon-meta
added a commit
to kwanghoon-meta/pytorch
that referenced
this pull request
May 29, 2024
…127309) Summary: X-link: pytorch/torchrec#2046 After QAT is completed or given pre-tuned weight observer via tunable PTQ algorithm, it should not over-write again with a given weight, at least for static QAT never. Dynamic QAT also does not require to re-run weight observer again by design. This is a fix Test Plan: Signals ``` buck2 run caffe2/test:test_mobile_optimizer ``` Reviewed By: jerryzh168 Differential Revision: D57747749
|
This pull request was exported from Phabricator. Differential Revision: D57747749 |
PaulZhang12
pushed a commit
that referenced
this pull request
Jun 5, 2024
Summary: X-link: pytorch/pytorch#127309 Pull Request resolved: #2046 After QAT is completed or given pre-tuned weight observer via tunable PTQ algorithm, it should not over-write again with a given weight, at least for static QAT never. Dynamic QAT also does not require to re-run weight observer again by design. This is a fix Reviewed By: jerryzh168 Differential Revision: D57747749 fbshipit-source-id: 231937f64c6dc53cc79b35bb94534fdaa84e7da1
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:
After QAT is completed or given pre-tuned weight observer via tunable PTQ algorithm, it should not over-write again with a given weight, at least for static QAT never.
Dynamic QAT also does not require to re-run weight observer again by design.
This is a fix
Differential Revision: D57747749