12:00
2026-09-08
research.ibm.com
artificial-intelligence
How llm-d makes the most of the hardware you already have
IBM Research and Red Hat used the open-source llm-d framework to deploy GLM-5.2, an approximately 753-billion-parameter mixture-of-experts model, on 544 NVIDIA H100 GPUs, serving up to 3,000 concurren…