flashinfer.comm.free_shared_buffer

flashinfer.comm.free_shared_buffer(pointers: List[int], group: ProcessGroup | None = None) → None

Free a shared buffer previously created by create_shared_buffer().

Each rank releases only its rank-local allocation; the IPC-mapped peer pointers must not be freed here.

Parameters:

• pointers (list[int]) – Per-rank pointer list returned by create_shared_buffer().

• group (torch.distributed.ProcessGroup, optional) – Process group used during allocation. Defaults to dist.group.WORLD.