{"categories":[{"label":"Artificial Intelligence","url":"https://skillfed.io/packages/category/scientific-engineering-artificial-intelligence/6"}],"enrichment":{"capability":"A PyTorch quantization backend that reduces model size and memory by converting weights and activations to lower-precision integer or float8 formats while maintaining inference accuracy.","skillfed_tags":["model-compression","quantization","inference-optimization"],"use_cases":["Quantize large models to int4 or int8 to reduce memory requirements and fit models on resource-constrained devices.","Compress model transformers to float8 for faster inference while preserving accuracy.","Calibrate and fine-tune quantized models on representative data to recover accuracy lost during quantization.","Serialize quantized model weights to safetensors format for efficient storage and distribution.","Deploy quantized models by reducing memory footprint and leveraging accelerated kernels on CUDA."],"what_it_does":"Optimum Quanto is a PyTorch quantization backend that converts trained models to lower-precision representations\u2014int2, int4, int8, or float8 for weights and activations\u2014to reduce memory footprint and accelerate inference. It integrates with the optimum framework, offering both high-level APIs and a low-level API for vanilla PyTorch models. The package supports a full workflow: quantize a model, optionally calibrate activations on representative data, fine-tune if needed, freeze weights to integer values, and serialize using safetensors or pickle.\n\nDesigned for eager-mode execution (works with non-traceable models), Quanto automatically inserts quantization stubs and operations into the model graph. It supports mixed-precision matrix multiplications on CUDA (int8-int8, fp16-int4, bf16-int8, bf16-int4) and aims for accuracy comparable to full-precision models when using int8 or float8 weights with float8 activations. The package is actively maintained but still pre-alpha; torch.compiler compatibility and dynamic activation smoothing are listed as not yet implemented.","worth_installing":"Yes, if you need to quantize PyTorch models for inference efficiency. The package is actively maintained, has no known vulnerabilities, and offers both high-level integration and low-level control. Install with caution if you depend on torch.compile or require production-grade stability\u2014it is pre-alpha and some features remain unimplemented."},"id":"optimum-quanto","links":{"html":"https://skillfed.io/packages/optimum-quanto","md":"https://skillfed.io/packages/optimum-quanto.md","pypi":"https://pypi.org/project/optimum-quanto/"},"maintenance":{"status":"active"},"meta":{"latest_release":"2025-03-06","license_spdx":null,"license_treatment":"permissive","name":"optimum-quanto","python_support":"supports_current","summary":"A pytorch quantization backend for optimum."},"popularity":{"monthly_downloads":292491,"position":7963,"tier":"top_15000"},"security":{"n_vulnerabilities":0},"version":"0.2.7"}