Handle meta tensors in FX quantization #2622
Closed
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: D66895899 |
kausv
added a commit
to kausv/pytorch
that referenced
this pull request
Dec 10, 2024
Summary: X-link: pytorch/torchrec#2622 If module being quantized contains a some meta tensors and some tensors with actual device, we should not fail quantization. Quantization should also not fail if new quantized module is created on a meta device. Test Plan: ``` buck run fbcode//mode/dev-nosan fbcode//torchrec/fb/quant/tests:test_embedding_modules ``` Differential Revision: D66895899
|
This pull request was exported from Phabricator. Differential Revision: D66895899 |
kausv
force-pushed
the
export-D66895899
branch
from
a58d82c to
1897723
Compare
kausv
force-pushed
the
export-D66895899
branch
from
1897723 to
6d38b7d
Compare
kausv
added a commit
to kausv/torchrec
that referenced
this pull request
Dec 19, 2024
Summary: X-link: pytorch/pytorch#142262 If module being quantized contains a some meta tensors and some tensors with actual device, we should not fail quantization. Quantization should also not fail if new quantized module is created on a meta device. If devices contain meta, copying from meta to meta is not necessary, copying from another device to meta can be skipped. Differential Revision: D66895899
|
This pull request was exported from Phabricator. Differential Revision: D66895899 |
kausv
added a commit
to kausv/pytorch
that referenced
this pull request
Dec 19, 2024
Summary: X-link: pytorch/torchrec#2622 If module being quantized contains a some meta tensors and some tensors with actual device, we should not fail quantization. Quantization should also not fail if new quantized module is created on a meta device. If devices contain meta, copying from meta to meta is not necessary, copying from another device to meta can be skipped. Test Plan: ``` buck run fbcode//mode/dev-nosan fbcode//torchrec/fb/quant/tests:test_embedding_modules ``` Differential Revision: D66895899
kausv
added a commit
to kausv/torchrec
that referenced
this pull request
Dec 19, 2024
Summary: X-link: pytorch/pytorch#142262 If module being quantized contains a some meta tensors and some tensors with actual device, we should not fail quantization. Quantization should also not fail if new quantized module is created on a meta device. If devices contain meta, copying from meta to meta is not necessary, copying from another device to meta can be skipped. Differential Revision: D66895899
kausv
force-pushed
the
export-D66895899
branch
from
6d38b7d to
edd3880
Compare
kausv
added a commit
to kausv/pytorch
that referenced
this pull request
Dec 19, 2024
Summary: X-link: pytorch/torchrec#2622 If module being quantized contains a some meta tensors and some tensors with actual device, we should not fail quantization. Quantization should also not fail if new quantized module is created on a meta device. If devices contain meta, copying from meta to meta is not necessary, copying from another device to meta can be skipped. Test Plan: ``` buck run fbcode//mode/dev-nosan fbcode//torchrec/fb/quant/tests:test_embedding_modules ``` Differential Revision: D66895899
|
This pull request was exported from Phabricator. Differential Revision: D66895899 |
kausv
force-pushed
the
export-D66895899
branch
from
edd3880 to
28bbf9b
Compare
kausv
added a commit
to kausv/torchrec
that referenced
this pull request
Dec 21, 2024
Summary: X-link: pytorch/pytorch#142262 If module being quantized contains a some meta tensors and some tensors with actual device, we should not fail quantization. Quantization should also not fail if new quantized module is created on a meta device. If devices contain meta, copying from meta to meta is not necessary, copying from another device to meta can be skipped. Differential Revision: D66895899
kausv
added a commit
to kausv/pytorch
that referenced
this pull request
Dec 21, 2024
Summary: X-link: pytorch/torchrec#2622 If module being quantized contains a some meta tensors and some tensors with actual device, we should not fail quantization. Quantization should also not fail if new quantized module is created on a meta device. If devices contain meta, copying from meta to meta is not necessary, copying from another device to meta can be skipped. Test Plan: ``` buck run fbcode//mode/dev-nosan fbcode//torchrec/fb/quant/tests:test_embedding_modules ``` Differential Revision: D66895899
|
This pull request was exported from Phabricator. Differential Revision: D66895899 |
kausv
added a commit
to kausv/pytorch
that referenced
this pull request
Dec 21, 2024
Summary: X-link: pytorch/torchrec#2622 If module being quantized contains a some meta tensors and some tensors with actual device, we should not fail quantization. Quantization should also not fail if new quantized module is created on a meta device. If devices contain meta, copying from meta to meta is not necessary, copying from another device to meta can be skipped. Test Plan: ``` buck run fbcode//mode/dev-nosan fbcode//torchrec/fb/quant/tests:test_embedding_modules ``` Reviewed By: emlin Differential Revision: D66895899
Summary: X-link: pytorch/pytorch#142262 If module being quantized contains a some meta tensors and some tensors with actual device, we should not fail quantization. Quantization should also not fail if new quantized module is created on a meta device. If devices contain meta, copying from meta to meta is not necessary, copying from another device to meta can be skipped. Reviewed By: emlin Differential Revision: D66895899
kausv
force-pushed
the
export-D66895899
branch
from
28bbf9b to
048a03b
Compare
|
This pull request was exported from Phabricator. Differential Revision: D66895899 |
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:
X-link: pytorch/pytorch#142262
If module being quantized contains a some meta tensors and some tensors with actual device, we should not fail quantization.
Quantization should also not fail if new quantized module is created on a meta device.
Differential Revision: D66895899