[Torch] Drop PTQuantizerInsertionCommand
#2584
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
NNCF PT
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## develop #2584 +/- ##
===========================================
- Coverage 91.16% 84.90% -6.26%
===========================================
Files 494 494
Lines 45350 45368 +18
===========================================
- Hits 41342 38521 -2821
- Misses 4008 6847 +2839
... and 59 files with indirect coverage changes
Flags with carried forward coverage won't be shown. Click here to find out more.
|
alexsu52
reviewed
Mar 20, 2024
daniil-lyakhov
force-pushed
the
dl/torch/remove_pt_qauntizer_insertion_command
branch
from
1281a0d to
317f263
Compare
daniil-lyakhov
force-pushed
the
dl/torch/remove_pt_qauntizer_insertion_command
branch
from
d3c03b0 to
9ec57fd
Compare
daniil-lyakhov
commented
Mar 25, 2024
AlexanderDokuchaev
approved these changes
Apr 2, 2024
alexsu52
pushed a commit
that referenced
this pull request
Apr 25, 2024
On top of #2584 ### Changes `NNCFNetwork.transformation_layout` method is introduced ### Reason for changes To make it possible to collect applied transformation commands from a modified `NNCFNetwork` ### Related tickets 129586 ### Tests TestGetAppliedModificationCommands
alexsu52
pushed a commit
that referenced
this pull request
May 6, 2024
On top of #2584 #2595 ### Changes * `serialize_transformations` and `load_transformations` functions are introduced: `serialize_transformations` could serialize `PTTransformationLayout` to a dict which could be serialized by json; serialized transformation could be recovered by the `load_transformations` function. * `StatefullTorchModuleInterface` is introduced to make it possible to serialize all compression modules for quantization, sparisification, weights compression and pruning algorithms * Quantizers are created with scale shape specified in the quantization spec ### Reason for changes * To make it possible to serialize/deserialize PT nncf transformations * To make it possible to serialize/deserialize compression modules which are the part of each transformation * To align scales shapes after `nncf.quantize` and quantizes initialization ### Related tickets 129586 ### Tests * tests/torch/test_serialization.py * tests/torch/test_serialization.py * tests/torch/test_serialization.py
Merged
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.
Preparation for #2531
Changes
PTQuantizerInsertionCommandis removed and replaced with create_quantizer_insertion_command functionSharedFNInsertionCommandupdates with one new attribute: compression_module_typeExtraOpCallHookdoesn't require context in constructor anymoreapply_quantizers_insertion_commands_transformationtoapply_insertion_transformationReason for changes
PTQuantizerInsertionCommandbySharedFNInsertionCommandExtraOpCallHookoutside of thePTModelTransformerRelated tickets
2531
Tests
1)
test_quantizer_insertion_transformationis updated2) -
3)
test_shared_fn_insertion_pointis updated4)
test_pt_insertion_commandis introduced