[PT] change api for get_config and load_from_config #3359
Merged
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
github-actions
bot
added
documentation
AlexanderDokuchaev
force-pushed
the
ad/pt_save_load_api
branch
from
57f8c5e to
e448ac0
Compare
AlexanderDokuchaev
requested review from
alexsu52 and
daniil-lyakhov
and removed request for
a team
alexsu52
reviewed
Mar 20, 2025
README.md
Outdated
| @@ -283,7 +284,7 @@ resuming_checkpoint = torch.load(path_to_checkpoint) | |||
| nncf_config = resuming_checkpoint['nncf_config'] | |||
| state_dict = resuming_checkpoint['state_dict'] | |||
|
|
|||
| quantized_model = nncf.torch.load_from_config(model, nncf_config, example_input) | |||
| quantized_model = load_from_config(model, nncf_config, example_input) | |||
There was a problem hiding this comment.
IMHO: What do you think about such usage?
Suggested change
| quantized_model = load_from_config(model, nncf_config, example_input) | |
| quantized_model = nncf.torch.load_from_config(model, nncf_config, example_input) |
There was a problem hiding this comment.
It won't work
Backend-specific modules is not part of nncf namespace
import nncf
nncf.torch.load_from_config
# AttributeError: module 'nncf' has no attribute 'torch'There was a problem hiding this comment.
not in this pr
There was a problem hiding this comment.
What about
import nncf.torch
nncf.torch.load_from_config
?
There was a problem hiding this comment.
will works, but i prefer
from nncf.torch import load_from_config
load_from_config
README.md
Outdated
| @@ -271,7 +272,7 @@ quantized_model = nncf.quantize(model, calibration_dataset) | |||
| # Save quantization modules and the quantized model parameters | |||
| checkpoint = { | |||
| 'state_dict': model.state_dict(), | |||
| 'nncf_config': model.nncf.get_config(), | |||
| 'nncf_config': get_config(model), | |||
There was a problem hiding this comment.
IMHO: What do you think about such usage?
Suggested change
| 'nncf_config': get_config(model), | |
| 'nncf_config': nncf.torch.get_config(model), |
docs/usage/training_time_compression/quantization_aware_training/Usage.md
Outdated
Show resolved
Hide resolved
daniil-lyakhov
requested changes
Mar 21, 2025
docs/usage/training_time_compression/quantization_aware_training/Usage.md
Outdated
Show resolved
Hide resolved
daniil-lyakhov
approved these changes
Mar 21, 2025
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.
Changes
Add
get_configtonncf/torch/__init__.pyUse function
get_configandload_from_configfor new and old tracing asfrom nncf.torch import get_config, load_from_configTests
https://github.com/openvinotoolkit/nncf/actions/runs/13974357105