Story
arxiv_cs_cl ยท Nov 17, 2026 ยท paper
arxiv.orgNov 17, 2026
original source linked
In brief
Post-training quantization is the standard way to serve large language models at low cost. However, the best quantization recipe differs across models and precisions. As a result, experts must redesign it for every ne...
Feed lens
agentharnessevaluation