-
Notifications
You must be signed in to change notification settings - Fork 250
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add SmoothQuant and ChannelAlignment to HyperparameterTuner #2154
Add SmoothQuant and ChannelAlignment to HyperparameterTuner #2154
Conversation
Codecov Report
Additional details and impacted files@@ Coverage Diff @@
## develop #2154 +/- ##
===========================================
+ Coverage 36.57% 36.62% +0.04%
===========================================
Files 484 486 +2
Lines 43310 43373 +63
===========================================
+ Hits 15841 15885 +44
- Misses 27469 27488 +19
|
a0e42ff
to
cbeb182
Compare
nncf/quantization/algorithms/hyperparameter_tuner/param_grid.py
Outdated
Show resolved
Hide resolved
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I'm OK with this solution. Please clean code and write doc strings.
183412a
to
8575880
Compare
b1da295
to
5670c04
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
5346d9b
to
e95b8a2
Compare
Build: 10740 |
for algorithm in self.first_stage_algorithms: | ||
if isinstance(algorithm, SmoothQuant) and backend != BackendType.OPENVINO: | ||
nncf_logger.debug(f"{backend.name} does not support SmoothQuant algorithm yet.") | ||
continue | ||
|
||
if isinstance(algorithm, ChannelAlignment) and backend != BackendType.OPENVINO: | ||
nncf_logger.debug(f"{backend.name} does not support ChannelAlignment algorithm yet.") | ||
continue |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks like this part is missing in the new realization, quantization of transformers for torch backend is failing because pipeline tries to apply smoothquant
Changes
Pipeline
class. To use the algorithm with theHyperparameterTuner
, it should be wrapped within aPipeline
object.Reason for changes
Related tickets
Ref: 117471
Tests