github:zechenzhangAGI/AI-research-SKILLs · first committed 2025-11-25 · source · badge
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.
Listed, not yet scored. This skill has no public model test yet. It is in the scoring queue; submitted skills go first, then the most-installed.
1 commit to this file on GitHub (newest first).