https://myvirtualcloud.net/tags/gpu-scheduling/Recent content in GPU Scheduling on myvirtualcloud.netHugoen-usAndre LeiboviciThu, 10 Sep 2026 09:00:00 +1200https://myvirtualcloud.net/handing-one-nodes-gpus-to-hami-without-touching-the-live-models/Thu, 10 Sep 2026 09:00:00 +1200https://myvirtualcloud.net/handing-one-nodes-gpus-to-hami-without-touching-the-live-models/<p>The box has four Blackwell RTX PRO 6000s in it. Two are Server Edition at 600 W, two are Max-Q Workstation Edition at 300 W. Kubernetes advertised four identical <code>nvidia.com/gpu</code> and handed out whichever card it felt like.</p> <p>For a single notebook that is fine. For tensor parallelism across two cards it is not. A mixed pair paces every collective at the slower card, so a TP=2 deployment that lands on one SE and one Max-Q quietly runs at Max-Q speed forever. That was the blocker on a research AI platform we run for a New Zealand university: three GPU nodes, two of them carrying eight H200s each and serving a live model to researchers, one RTX node for development and benchmarking.</p>