Options for creating a sampled-token readback ring.
The ring is intended for batched GPU->CPU token-id readback where each token is represented as int32.
Maximum number of token ids (int32) per submitted batch.
Optional
Number of staging slots in the ring. Defaults to 3 when unspecified.
Options for creating a sampled-token readback ring.
The ring is intended for batched GPU->CPU token-id readback where each token is represented as int32.