{
  "name": "cupynumeric-parallel-data-load",
  "version": "0.1.0",
  "description": "Load a sharded, on-disk dataset (sharded .npy, Parquet/Arrow, raw binary, sharded HDF5, custom layouts) into a distributed cuPyNumeric ndarray via a manual partition + leaf @task launch with CPU/OMP/GPU variants. Use when no single-call loader fits, including when per-shard row counts differ across files. Prefer cupynumeric.load or legate.io.hdf5.from_file when they apply.",
  "keywords": [
    "github-import",
    "NVIDIA",
    "skills"
  ],
  "license": "CC-BY-4.0 OR Apache-2.0",
  "source": {
    "repo": "NVIDIA/skills",
    "ref": "main",
    "path": "skills/cupynumeric-parallel-data-load",
    "url": "https://github.com/NVIDIA/skills/tree/main/skills/cupynumeric-parallel-data-load"
  }
}