class ArenaEvery output whose length only the call knows, the embeddings, the states and their offsets, lands in a uform.Arena you pass, and the verb answers views over it without copying. uform.Arena(executor) places it where that executor computes, decided once, and uform.Arena() makes host pages for the calling thread.
Each call rewinds its arena, so the previous call’s views die and a steady loop allocates once.
To keep a result past the next call, pass that call another arena; an arena serves one call at a time, so each deferred call needs its own.
A NumPy array or memoryview over an output pins its arena as a memoryview pins a bytearray, so the next call naming that arena raises ContendedError until the export is released.
A stale output raises InvalidArgumentError when read.
An arena from a VRAM executor holds device memory: its views export __cuda_array_interface__ for CuPy, PyTorch or Numba, and host reads raise DeviceError.
arena = uform.Arena(executor)
for batch in batches:
encoded = model.on(executor).text_encode(batch, arena) # rewinds: the last batch's views are gone
index.add(np.array(encoded.embeddings)) # a copy, so nothing pins the arenaAPI
Types
ArenaThe memory every output whose length scales with a call lands in, rewound by each call handed it.
ClassArenaBufferOne output a call left in an Arena, readable until a later call rewinds it.5
class ArenaBuffer__buffer__Host memory only; device memory raises DeviceError, a rewound arena InvalidArgumentError.
def __buffer__(flags: int, /) -> memoryview__len__Rows.
__dlpack__A DLPack capsule over the output in place; the arena refuses to rewind until the consumer lets go.
def __dlpack__(
*,
stream: Any = None,
max_version: tuple[int, int] | None = None,
dl_device: tuple[int, int] | None = None,
copy: bool | None = None,
) -> Any__dlpack_device__The DLPack device type and ID the output lives on.
def __dlpack_device__() -> tuple[int, int]