LLM News Today

Blog Towards Blackwell-Native 8-bit and 4-bit RL: End-to-End MXFP8 and NVFP4 RL in Miles TL;DR: We implemented two Blackwell-native RL recipes in Miles: end-to-end MXFP8 and per-token NVFP4 for MoE experts. Both are supported by fine-grained precision control across checkpoint conversion,... Ziang Li, humans& and Miles Team

By LMSYS Blog··Qwen / Alibaba

This story was filed as a headline only — the news service holds no English full text for it. Read the original at LMSYS Blog →