Vector Post-Training Quantization (VPTQ) is a novel Post-Training Quantization method that leverages Vector Quantization to high accuracy on LLMs at an extremely low bit-width (<2-bit). VPTQ can ...
A Python library for generating unique, distributed IDs using a modified Snowflake algorithm. This library allows for easy generation of Snowflake IDs, encoding/decoding to Base62, and extracting ...