[PTQ][Common] Use inference_nncf_graph instead nncf_graph in get_weights #2862
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
|
Onnx tests diff: |
github-actions
bot
added
NNCF PT
daniil-lyakhov
force-pushed
the
dl/ptq/fix_weights_nodes_collection
branch
from
11b19f0 to
d1de35e
Compare
daniil-lyakhov
force-pushed
the
dl/ptq/fix_weights_nodes_collection
branch
2 times, most recently
from
013bea4 to
d8d043e
Compare
|
Turns out some operations on constant paths should be quantized (like positional embedding in GPT-2 model), so this fix is invalid |
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Outdated suggestions cannot be applied.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
Use inference_nncf_graph instead nncf_graph in get_weights
Reason for changes
To avoid quantizing weight nodes that are present in
nncf_graphand absent ininference_nncf_graphRelated tickets
#2766
Tests
test_ptq_params: test_constant_branch_weighted_node_quantization is introduced