[PyPer][quant] Move quantized embedding operators to OSS. (#4606) #40076
Conversation
|
This pull request was exported from Phabricator. Differential Revision: D21949828 |
💊 CI failures summary and remediationsAs of commit 3e0f0b9 (more details on the Dr. CI page):
ci.pytorch.org: 1 failedThis comment was automatically generated by Dr. CI (expand for details).Follow this link to opt-out of these comments for your Pull Requests.Please report bugs/suggestions on the GitHub issue tracker or post in the (internal) Dr. CI Users group. This comment has been revised 52 times. |
radkris-git
force-pushed
the
export-D21949828
branch
from
dea7273 to
c1889e9
Compare
|
This pull request was exported from Phabricator. Differential Revision: D21949828 |
1 similar comment
|
This pull request was exported from Phabricator. Differential Revision: D21949828 |
radkris-git
force-pushed
the
export-D21949828
branch
from
c1889e9 to
881993f
Compare
radkris-git
force-pushed
the
export-D21949828
branch
from
881993f to
9026a23
Compare
|
This pull request was exported from Phabricator. Differential Revision: D21949828 |
|
This pull request was exported from Phabricator. Differential Revision: D21949828 |
radkris-git
force-pushed
the
export-D21949828
branch
from
9026a23 to
52a50d1
Compare
|
This pull request was exported from Phabricator. Differential Revision: D21949828 |
radkris-git
force-pushed
the
export-D21949828
branch
from
52a50d1 to
09ad248
Compare
|
This pull request was exported from Phabricator. Differential Revision: D21949828 |
radkris-git
force-pushed
the
export-D21949828
branch
from
09ad248 to
2433267
Compare
|
This pull request was exported from Phabricator. Differential Revision: D21949828 |
radkris-git
force-pushed
the
export-D21949828
branch
from
2433267 to
26f3cb9
Compare
radkris-git
force-pushed
the
export-D21949828
branch
from
26f3cb9 to
13aec1c
Compare
|
This pull request was exported from Phabricator. Differential Revision: D21949828 |
radkris-git
force-pushed
the
export-D21949828
branch
from
13aec1c to
61e19a5
Compare
|
This pull request was exported from Phabricator. Differential Revision: D21949828 |
radkris-git
force-pushed
the
export-D21949828
branch
from
61e19a5 to
4baad28
Compare
|
This pull request was exported from Phabricator. Differential Revision: D21949828 |
1 similar comment
|
This pull request was exported from Phabricator. Differential Revision: D21949828 |
radkris-git
force-pushed
the
export-D21949828
branch
2 times, most recently
from
9f92992 to
5cf22b8
Compare
|
This pull request was exported from Phabricator. Differential Revision: D21949828 |
radkris-git
force-pushed
the
export-D21949828
branch
from
5cf22b8 to
02ca2d7
Compare
|
This pull request was exported from Phabricator. Differential Revision: D21949828 |
radkris-git
force-pushed
the
export-D21949828
branch
from
02ca2d7 to
e156800
Compare
|
This pull request was exported from Phabricator. Differential Revision: D21949828 |
Summary: Pull Request resolved: pytorch#40076 Pull Request resolved: pytorch/glow#4606 [PyPer][quant] Add quantized embedding operators to OSS. This is the first step in supporting Graph Mode Quantization for EmbeddingBag. At a high level, the next steps would be a) Implementation of Embedding prepack/unpack operators, b) Implementation of torch.nn.quantized.dynamic.EmbeddingBag Module, c) Implementation of torch.nn.quantized.EmbeddingBag Module, d) Implementation (modification) of IR passes to support graph quantization of EmbeddingBag module. More in-depth details regarding each step will be in the follow up diffs. Consider this as an initial diff that moves operators to respective places that's required for us to proceed. Test Plan: ```buck test mode/no-gpu caffe2/test:quantization -- --stress-runs 100 test_embedding_bag``` Reviewed By: supriyar Differential Revision: D21949828 fbshipit-source-id: 47762368b5d08fe38a5e529b58452995477a6e1b
|
This pull request was exported from Phabricator. Differential Revision: D21949828 |
radkris-git
force-pushed
the
export-D21949828
branch
from
e156800 to
3e0f0b9
Compare
|
This pull request has been merged in f41173b. |
3 participants
Summary:
Pull Request resolved: pytorch/glow#4606
[PyPer][quant] Move quantized embedding operators to OSS.
This is the first step in supporting Graph Mode Quantization for EmbeddingBag.
The next steps would be
a) Implementation of Embedding prepack/unpack operators,
b) Implementation of torch.nn.quantized.dynamic.EmbeddingBag Module,
c) Implementation of torch.nn.quantized.EmbeddingBag Module,
d) Implementation (modification) of IR passes to support graph quantization of EmbeddingBag module.
More in-depth details regarding each step will be in the follow up diffs. Consider this as an initial diff that moves operators to respective places that's required for us to proceed.
Test Plan:
buck test test:quantization -- '.*TestQuantizedEmbeddingBag.*Differential Revision: D21949828