Function llama_batch_get_one

llama_cpp/llama_cpp.py:2988–2997

Return batch for single sequence of tokens NOTE: this is a helper function to facilitate transition to the new batch API - avoid using it

(
    tokens: CtypesArray[llama_token],
    n_tokens: Union[ctypes.c_int, int],
    /,
)

    llama_batch,
)
def llama_batch_get_one(
    tokens: CtypesArray[llama_token],
    n_tokens: Union[ctypes.c_int, int],
    /,
) -> llama_batch:
    """Return batch for single sequence of tokens

    NOTE: this is a helper function to facilitate transition to the new batch API - avoid using it
    """
    ...


# // Allocates a batch of tokens on the heap that can hold a maximum of n_tokens