AutoRound
JSON →AutoRound is an advanced weight-only quantization algorithm for large language models (LLMs), providing up to 4-bit quantization with minimal accuracy loss. Current version 0.13.0 supports various Intel and AMD GPUs, as well as CPUs. The package is under active development by Intel.
Traffic · last 30 days stale · no recent hits
total hits 17
actors 5 distinct systems
last hit 17d ago AhrefsBot
top countries 🇸🇬 Singapore · 🇺🇸 United States · 🇫🇷 France · 🇨🇦 Canada · VN