{"library":"diffq","type":"library","category":null,"description":"DiffQ is a differentiable quantization framework for PyTorch that provides tools to quantize PyTorch models, primarily focusing on large language models (LLMs) and computer vision models. It enables quantization-aware training and leverages various quantization methods like GPTQ, HQQ, and AWQ. Currently at version 0.2.4, it has seen active development, especially in late 2023, with periodic releases addressing new features and bug fixes.","language":"python","status":"active","version":"0.2.4","tags":["pytorch","quantization","differentiable","machine-learning","deep-learning","llm","compression"],"last_verified":"Tue May 26","install":[{"cmd":"pip install diffq","imports":["from diffq import DiffQModel","from diffq import BaseQuantizationConfig","from diffq.quantizers import GPTQQuantizer","from diffq.models import ViTForImageClassification"]},{"cmd":"pip install diffq[hqq_ext] # for HQQ support\npip install diffq[awq_ext] # for AWQ support\npip install bitsandbytes # for 8-bit quantization","imports":[]}],"homepage":null,"github":"https://github.com/facebookresearch/diffq","docs":null,"changelog":null,"pypi":"https://pypi.org/project/diffq/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":55,"avg_install_s":77.1,"avg_import_s":null,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/diffq/compatibility"}}