QDA: Agent-Based Closed-Loop System Designs LLM Quantization Recipes
A new arXiv paper introduces QDA, a closed-loop agentic system that designs post-training quantization recipes for large language models, addressing how optimal quantization choices vary across models.
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-11-19 05:00 · arXiv cs.LG
QDA: Closed-Loop LLM Quantization Design with Agents