What's Changed
* Internal clean up. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/1
* Fix oss unit test in Python 3.9 for calibrator.py. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/3
* Relax the compatibility check for tensor transformation params. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/2
* Fix Python3.9 error in calibrator.py by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/5
* Fix comments and docstring formatting in qtyping.py by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/6
* Fix comments and docstring formatting in naive_min_max_quantize.py by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/7
* Add depthwise conv2d support. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/10
* Add build_pypi.yml in GitHub action workflow. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/17
* Move nested functions outside of materialize_standard_op by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/12
* Fix a bug in recipe manager. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/16
* Transform TODOs style by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/14
* Add transpose support by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/19
* Internal test support. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/22
* Enable int4 DRQ for EmbeddingLookup by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/24
* Fix order in the list returned by materialize_standard_op by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/25
* Support ADD op in quantization tool. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/20
* Refactor materialize_softmax to materialize_op_with_output_activation_constraint. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/23
* Add tanh support by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/26
* Trigger github CI to run on pull request. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/27
* Fix a bug in CONV2D tests. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/18
* Fix comments and docstring formatting in params_generator.py by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/30
* Switch order of float and quantized for comparison function. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/29
* No public description by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/34
* Add a skip_checks option to OpQuantizationConfig. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/32
* Support SUB op in quantization tool. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/21
* Add BMM op to the SRQ list. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/38
* Remove full-integer requirement for calibrator by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/35
* Check parameters for compatibility only if they exists by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/36
* Support RSQRT op in quantization tool by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/41
* Format the JSON recipes. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/46
* Support STRIDED_SLICE op in quantization tool by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/43
* Add split op support by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/44
* Fix a bug in ParamsGenerator. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/47
* Add i4 EmbeddingLookup to the supported DRQ op list by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/53
* Prevent in-place modification of signature_input_data by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/49
* Fixed a bug to allow input tensors to be quantized for full integer models. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/51
* Refactor `materialize_fc_conv` to separate bias materialization. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/57
* Add conv2d_transpose support. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/54
* Add conv2d_transpose support. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/59
* Add a sample default policy for configuration checks, along with the implementation to load it. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/60
* Fix a bug in transformation_instruction_generator.py by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/61
* Set the max precision of quantization scale when quantize a tensor (1e-6 for int8 and 1e-8 for int16). by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/62
* Expand default config check policy with DRQ op checking and replace hardcoded logic. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/66
* add frontend support for emulated subchannel by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/56
* Refactor, organize, and add comments to MNIST by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/65
* Add testing functions for ignored inputs/outputs by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/69
* Expand default config check policy with SRQ op checking and replace hardcoded logic. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/67
* Expand default config check policy with Weight-Only op checking and replace hardcoded logic. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/68
* Check if input model is already quantized by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/70
* Fix how ignored inputs/outputs are processed by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/63
* Add utils to get input/output/constant tensor names from the model. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/71
* Fix the default_af32w4float_recipe.json. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/80
* Internal clean ups. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/82
* Add ComparisonResult class and process_comparison_result function. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/72
* Remove the nested folder structure when save the quantized model. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/83
* Fix for model_validator to check dtype of tensor. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/84
* Save `ComparisonResult` object to be used as the input for model explorer. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/79
* Add conftest.py to fix pytest error. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/87
* Add some blockwise quantization to default policy. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/77
* Allow Calibrator to accept custom qsv_update_func. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/86
* Remove un-needed files. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/89
* add sample test image for isnet example by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/90
* Remove temporary fix from ParamsGenerator by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/91
* Add a function to update the qsv with minimum min values and maximum max values. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/88
* skip non-native numpy tensor type when validating by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/94
* Fix a bug for calibration process. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/92
* Add an option to use reference kernel for numerical validation. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/96
* Rename `default_af32w8int_recipe.json` to `dynamic_wi8_afp32_recipe.json` by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/98
* fix shape issue for emulated subchannel quantization by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/101
* Remove suffix `_quantized` in the result tflite file. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/103
* Add tensor name checks in params generator. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/100
* No allocate_tensor for _check_is_float_model by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/105
* Removes the interpreter dependency from quantizer initialization process. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/109
* Add input/output operators to the subgraph. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/102
* Ignore Lookup index when quantizing embedding_lookup op. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/110
* Add getting_started colab to OSS (dynamic quantization for MNIST model) by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/111
* Improve the op coverage documentation by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/113
* Remove obsolete `check_weight_only_config`, `check_drq_config`, `check_srq_config` functions by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/97
* Elaborate getting_started colab by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/116
* Add end to end test for input output op quantization. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/114
* Add colab with torch conversion and quantization by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/118
* Move Colabs and documentation to top-level folder by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/117
* Add test_data folder for selective_quantization_isnet colab by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/119
* Remove weight-only quantization from selective_quantization_isnet colab by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/122
* Internal document changes. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/123
* Add FP16 tfl.embedding_lookup support by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/121
* Small cleanup of the torch Colab. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/125
* Add `export_model` method to the quantization by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/124
* Utilize `export_model` method in Colabs by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/126
* Some cleanup of the getting_started Colab. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/128
* Improvements to the selective quantization Colab by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/129
* Add links to open in Colab and view source on GitHub. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/132
* Link to the Colabs from the README. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/130
* Additional cleanup of the docs by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/131
* Some more edits to the top-level README. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/134
* Small cleanup of docs by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/136
* Add Logistic OP to AI Edge Quantizer. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/133
* Reduce memory usage in Quantizer by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/138
* Extend interpreter utils to support multi-signature models. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/137
* Add LOGISTIC to the list of supported ops in README. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/142
* Add getting started colab to nightly testing by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/141
* Fix nightly testing workflow for getting started colab by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/145
* Add the quantized two signature model for testing purposes. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/143
* Refactor ComparisonResult to support multiple signatures. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/144
* Fix the error in the selective quantization colab. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/149
* Add model size reduction information to ComparisonResult. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/150
* Add weight_only support for bmm op. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/156
* Add EMBEDDING_LOOKUP to weightonly_wi4_afp32 policy. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/157
* Add INT4 Conv to supported policy by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/154
* Reduce quantization time for large models by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/159
* Implement multi-signature calibration by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/160
* Check if calibration result has sufficient QSV before quantization. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/161
* Add recipe for dynamic legacy compatibility by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/163
* Add dynamic_legacy_wi8_afp32 recipe to recipe module by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/164
* Add static quantization for EMBEDDING_LOOKUP in Quantizer by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/169
* Add full integer quantization for SELECT_V2 in Quantizer by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/171
* Update README with newly added ops. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/172
* Enable packing only for the 4 bits case. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/173
* Enable calibration and model validation with XNNPACK by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/175
* Fix selective quantization Colab by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/176
* Enable quantization when op may contain tensors with zero-size array by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/178
* add quantize tensor with Blockwise data into transformation by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/177
* Refactor min/max quantize files by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/179
* front end change for native blockwise quantization by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/180
* Support py3.12 for ai_edge_quantizer. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/187
* Support py3.12 for ai_edge_quantizer. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/190
* Register dequantized weight recovery algorithm for FullyConnected and EmbeddingLookup. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/188
* Internal test cleanups. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/185
* Add full integer quantization for DYNAMIC_UPDATE_SLICE in Quantizer by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/191
* Internal test cleanups. by copybara-service in https://github.com/google-ai-edge/ai-edge-quantizer/pull/189
**Full Changelog**: https://github.com/google-ai-edge/ai-edge-quantizer/commits/v0.1.0