[Hardware] Replace torch.cuda.device_count/current_device/set_device API (#36145)

Signed-off-by: Kunshang Ji <jikunshang95@gmail.com>
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
This commit is contained in:
Kunshang Ji
2026-03-12 22:57:47 +08:00
committed by GitHub
parent 2e693f48e7
commit 53ec16a705
89 changed files with 254 additions and 219 deletions

View File

@@ -66,7 +66,7 @@ def _worker_parallel_launch(
**kwargs: P.kwargs,
) -> None:
rank = node_rank * world_local_size + local_rank
torch.cuda.set_device(local_rank)
torch.accelerator.set_device_index(local_rank)
device = torch.device("cuda", local_rank)
torch.distributed.init_process_group(
backend="cpu:gloo,cuda:nccl",