2x GH200 for LLM inference, Part 3: GLM-5.2, expert offload, and the CPU question (opens in new tab)
Feeds
David Noel Ng dnhkng.github.io
ML, Biotech, Hardware, and Coordination Problems. Sometimes I write about hard problems and how to solve them.
ML, Biotech, Hardware, and Coordination Problems. Sometimes I write about hard problems and how to solve them.