Verified record · from the answer index

hqq-quantization

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.

skill:orchestra-research/ai-research-skills/hqq-quantization · published by orchestra-research · source repository