def synchronize_rng_state()

in src/accelerate/utils/random.py [0:0]

• 69 lines of code
• 30 McCabe index (conditional complexity)

def synchronize_rng_state(rng_type: Optional[RNGType] = None, generator: Optional[torch.Generator] = None):
    # Get the proper rng state
    if rng_type == RNGType.TORCH:
        rng_state = torch.get_rng_state()
    elif rng_type == RNGType.CUDA:
        rng_state = torch.cuda.get_rng_state()
    elif rng_type == RNGType.XLA:
        assert is_torch_xla_available(), "Can't synchronize XLA seeds as torch_xla is unavailable."
        rng_state = torch.tensor(xm.get_rng_state())
    elif rng_type == RNGType.NPU:
        assert is_npu_available(), "Can't synchronize NPU seeds on an environment without NPUs."
        rng_state = torch.npu.get_rng_state()
    elif rng_type == RNGType.MLU:
        assert is_mlu_available(), "Can't synchronize MLU seeds on an environment without MLUs."
        rng_state = torch.mlu.get_rng_state()
    elif rng_type == RNGType.SDAA:
        assert is_sdaa_available(), "Can't synchronize SDAA seeds on an environment without SDAAs."
        rng_state = torch.sdaa.get_rng_state()
    elif rng_type == RNGType.MUSA:
        assert is_musa_available(), "Can't synchronize MUSA seeds on an environment without MUSAs."
        rng_state = torch.musa.get_rng_state()
    elif rng_type == RNGType.XPU:
        assert is_xpu_available(), "Can't synchronize XPU seeds on an environment without XPUs."
        rng_state = torch.xpu.get_rng_state()
    elif rng_type == RNGType.HPU:
        assert is_hpu_available(), "Can't synchronize HPU seeds on an environment without HPUs."
        rng_state = torch.hpu.get_rng_state()
    elif rng_type == RNGType.GENERATOR:
        assert generator is not None, "Need a generator to synchronize its seed."
        rng_state = generator.get_state()

    # Broadcast the rng state from device 0 to other devices
    state = AcceleratorState()
    if state.distributed_type == DistributedType.XLA:
        rng_state = rng_state.to(xm.xla_device())
        xm.collective_broadcast([rng_state])
        xm.mark_step()
        rng_state = rng_state.cpu()
    elif (
        state.distributed_type in CUDA_DISTRIBUTED_TYPES
        or state.distributed_type == DistributedType.MULTI_MLU
        or state.distributed_type == DistributedType.MULTI_SDAA
        or state.distributed_type == DistributedType.MULTI_MUSA
        or state.distributed_type == DistributedType.MULTI_NPU
        or state.distributed_type == DistributedType.MULTI_XPU
        or state.distributed_type == DistributedType.MULTI_HPU
    ):
        rng_state = rng_state.to(state.device)
        torch.distributed.broadcast(rng_state, 0)
        rng_state = rng_state.cpu()
    elif state.distributed_type == DistributedType.MULTI_CPU:
        torch.distributed.broadcast(rng_state, 0)

    # Set the broadcast rng state
    if rng_type == RNGType.TORCH:
        torch.set_rng_state(rng_state)
    elif rng_type == RNGType.CUDA:
        torch.cuda.set_rng_state(rng_state)
    elif rng_type == RNGType.NPU:
        torch.npu.set_rng_state(rng_state)
    elif rng_type == RNGType.MLU:
        torch.mlu.set_rng_state(rng_state)
    elif rng_type == RNGType.SDAA:
        torch.sdaa.set_rng_state(rng_state)
    elif rng_type == RNGType.MUSA:
        torch.musa.set_rng_state(rng_state)
    elif rng_type == RNGType.XPU:
        torch.xpu.set_rng_state(rng_state)
    elif rng_state == RNGType.HPU:
        torch.hpu.set_rng_state(rng_state)
    elif rng_type == RNGType.XLA:
        xm.set_rng_state(rng_state.item())
    elif rng_type == RNGType.GENERATOR:
        generator.set_state(rng_state)