{"categories":[{"label":"Artificial Intelligence","url":"https://skillfed.io/packages/category/scientific-engineering-artificial-intelligence/9"}],"enrichment":{"capability":"DiffQ performs differentiable quantization of PyTorch models using pseudo quantization noise, automatically tuning the number of bits per weight to balance model size and accuracy.","skillfed_tags":["model-compression","quantization","abandoned"],"use_cases":["Compress large transformer or CNN models for deployment on memory-constrained devices while maintaining accuracy","Automatically determine per-layer or per-group bit allocations during training without manual hyperparameter tuning","Export quantized models to TorchScript for optimized inference with reduced memory footprint","Research differentiable quantization methods and compare compression-accuracy tradeoffs across architectures","Reduce model size for distributed training or inference in bandwidth-limited environments"],"what_it_does":"DiffQ is a PyTorch quantization framework that reduces model size by automatically determining optimal bit-widths for individual weights or weight groups during training. It uses pseudo quantization noise injection to make the quantization process differentiable, allowing the bit allocation itself to be optimized as part of the training loop alongside model weights.\n\nThe package integrates with standard PyTorch training pipelines: you attach a DiffQuantizer to your model before creating the optimizer, then add a model-size penalty term to your loss function. During training, the quantizer learns which weights need more bits and which can use fewer, trading off compression against accuracy. At inference, it automatically switches to true quantized weights, and you can export the compressed model to disk or TorchScript format.","worth_installing":"No. The package is abandoned (last commit 2023-05-05) and licensed under CC-BY-NC 4.0, restricting use to non-commercial purposes only. Unless you are conducting non-commercial research and can tolerate no future updates, use an actively maintained quantization library instead."},"id":"diffq","links":{"html":"https://skillfed.io/packages/diffq","md":"https://skillfed.io/packages/diffq.md","pypi":"https://pypi.org/project/diffq/"},"maintenance":{"status":"abandoned"},"meta":{"latest_release":"2023-05-05","license_spdx":null,"license_treatment":"noncommercial","name":"diffq","python_support":"supports_current","summary":"Differentiable quantization framework for PyTorch."},"popularity":{"monthly_downloads":120635,"position":12015,"tier":"top_15000"},"security":{"n_vulnerabilities":0},"version":"0.2.4"}