This repository has been archived by the owner on May 1, 2023. It is now read-only.
Enable weights-only and activations-only post-training quantization for conv/linear modules #439
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
* Allow RangeLinearQuantWrapper to accept num_bits_acts = None, in which case it'll act as a simple pass-through during forward * In RangeLinearQuantParamLayerWrapper, if bits_activations is None and num_bits_params > 0, Perform quant and de-quant of the parameters instead of just quant.
* Enable activations only quantization for conv/linear modules. When PostTrainLinearQuantizer detects # bits != None for activations and # bits == None for weights, a fake-quantization wrapper will be used. * Allow passing 0 in the `--qe-bits-acts` and `--qe-bits-wts` command line arguments to invoke weights-only / activations-only quantization respectively. * Minor refactoring for clarity in PostTrainLinearQuantizer replace_* functions
guyjacob
changed the title
levzlotnik
approved these changes
Dec 8, 2019
This was referenced Dec 8, 2019
michaelbeale-IL
pushed a commit
that referenced
this pull request
Apr 24, 2023
* Weights-only PTQ:
* Allow RangeLinearQuantWrapper to accept num_bits_acts = None, in
which case it'll act as a simple pass-through during forward
* In RangeLinearQuantParamLayerWrapper, if bits_activations is None
and num_bits_params > 0, Perform quant and de-quant of the
parameters instead of just quant.
* Activations-only PTQ:
* Enable activations only quantization for conv/linear modules. When
PostTrainLinearQuantizer detects # bits != None for activations
and # bits == None for weights, a fake-quantization wrapper will
be used.
* Allow passing 0 in the `--qe-bits-acts` and `--qe-bits-wts` command
line arguments to invoke weights/activations-only quantization,
respectively.
* Minor refactoring for clarity in PostTrainLinearQuantizer's replace_*
functions
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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.
Same functionality as #356, but decided to take a different approach, which reuses the existing PTQ wrapper modules. This reduces code duplication and keeps the quantized model "similar" (in terms of modules used) when activations aren't quantized vs. when they are.
RangeLinearQuantWrapperto acceptnum_bits_acts = None, in which case it'll act as a simple pass-through during forward.RangeLinearQuantParamLayerWrapper, ifbits_activationsis None andnum_bits_params> 0, perform quant and de-quant of the parameters instead of just quant.PostTrainLinearQuantizerdetects # bits != None for activations and # bits == None for weights, a fake-quantization wrapper will be used.--qe-bits-actsand--qe-bits-wtscommand line arguments to invoke weights-only / activations-only quantization, respectively.PostTrainLinearQuantizer's internalreplace_*functions