{"library":"llmcompressor","type":"library","category":null,"description":"LLM Compressor (current version 0.10.0.1) is a Python library for compressing large language models, offering both training-aware and post-training techniques. Built on PyTorch and HuggingFace Transformers, it provides a flexible and user-friendly interface for researchers and practitioners to quickly experiment with techniques like quantization and sparsity. The library maintains an active development pace with frequent patch releases and regular feature updates.","language":"python","status":"active","version":"0.10.0.1","tags":["LLM","compression","quantization","sparsity","transformers","pytorch","deep learning","model optimization"],"last_verified":"Tue May 26","install":[{"cmd":"pip install llmcompressor","imports":["from llmcompressor.models import AutoModelForCausalLM","from llmcompressor.modifiers import QuantizationModifier","from llmcompressor.recipes import SparseMLRecipe","from llmcompressor.compression import Compressor","from transformers import AutoTokenizer"]},{"cmd":"pip install llmcompressor[autoround]","imports":[]}],"homepage":null,"github":"https://github.com/vllm-project/llm-compressor","docs":null,"changelog":null,"pypi":"https://pypi.org/project/llmcompressor/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":0,"avg_install_s":null,"avg_import_s":null,"wheel_type":null},"url":"https://checklist.day/v1/registry/llmcompressor/compatibility"}}