flashinfer.cake_gdn_nondet_train_kcp.is_cake_gdn_nondet_train_kcp_supported

flashinfer.cake_gdn_nondet_train_kcp.is_cake_gdn_nondet_train_kcp_supported(device: device | str | int | None = None) → bool

True when device (default: the current CUDA device) is an exported target of the package (sm_100a, sm_103a, sm_107a). False without CUDA, for a device that is not a CUDA device and for a device that cannot be queried. A package that fails to import raises: it is not reported as unsupported.

Parameters:

device (torch.device, str, int, optional) – Device to query; None selects the current CUDA device.