[quantization] Introduce wrapper for Qwen3VLTextDecoderLayer#566
Merged
mhs4670go merged 1 commit intoSamsung:mainfrom Mar 24, 2026
Merged
[quantization] Introduce wrapper for Qwen3VLTextDecoderLayer#566mhs4670go merged 1 commit intoSamsung:mainfrom
mhs4670go merged 1 commit intoSamsung:mainfrom
Conversation
613c233 to
be903b6
Compare
be903b6 to
cae5c77
Compare
9795d38 to
be93970
Compare
Contributor
|
@dvsav Seems CI test failed. |
This change introduces QuantQwen3VLTextDecoderLayer wrapper to support post-training quantization of Qwen3VLTextDecoderLayer operation. TICO-DCO-1.0-Signed-off-by: d.savchenkov <d.savchenkov@partner.samsung.com>
be93970 to
8da4c37
Compare
Contributor
Author
Hi @mhs4670go, |
mhs4670go
reviewed
Mar 24, 2026
| # Convert to quantized version | ||
| quantized_model = tico.quantization.convert(prepared_model, inplace=True) | ||
|
|
||
| # Compute PEIR (Peak Error-to-Input Ratio) between quantized model and original model |
Contributor
There was a problem hiding this comment.
Peak Error to Interval ratio. Seems other codes have mistakes. Let's fix them at once in another PR.
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This change introduces
QuantQwen3VLTextDecoderLayerwrapper to support post-training quantization ofQwen3VLTextDecoderLayermodule.Why?
Qwen3VLTextDecoderLayeris an essential part of Qwen model.Trying to quantize
Qwen3VLTextDecoderLayervia PTQ generates exceptionPTQQuantizer: no quantization wrapper for Qwen3VLTextDecoderLayer.What
This change introduces:
QuantQwen3VLTextDecoderLayer(tico/quantization/wrapq/wrappers/qwen_vl/quant_text_decoder_layer.py).class TestQuantQwen3VLTextDecoderLayer(test/quantization/wrapq/wrappers/qwen_vl/test_quant_text_decoder_layer.py) - skipped iftransformerspackage is not installed._CORE_MODULES(tico/quantization/wrapq/wrappers/registry.py).Qwen3VLTextDecoderLayerquantization and conversion to Circle (tico/quantization/wrapq/examples/qwen/quantize_text_decoder_layer.py).Unit Tests
Unit tests results with coverage information:
Coverage info (irrelevant files skipped):
Script for testing quantization and conversion to Circle