remote-compute-nvidia

Run GPU jobs on NVIDIA NIM microservices via host.compute.create('byoc:nvidia', ...). Covers both forms — self_hosted (an nvcr.io NIM container on a local GPU with --gpus all) and hosted (the fully-managed integrate.api.nvidia.com gateway, no local GPU) — sharing one submit→poll .result()→harvest flow. Load once you've decided to dispatch to NVIDIA NIM.