Skip to content

Commit 534b16a

Browse files
committed
fix docstring rendering
1 parent 64f154c commit 534b16a

File tree

1 file changed

+6
-6
lines changed

1 file changed

+6
-6
lines changed

cuda_core/cuda/core/experimental/_memory.pyx

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -563,15 +563,15 @@ class DeviceMemoryResource(MemoryResource):
563563
device memory resource does not own the pool (`is_handle_owned` is
564564
`False`), and closing the resource has no effect.
565565
566-
IPC-Enabled Memory Resources
567-
----------------------------
568-
If ``ipc_enabled=True`` is specified as an initializer option, the memory
569-
resource constructed will be capable of sharing allocations between
570-
processes. Sharing an allocation is a two-step procedure that involves
566+
Notes
567+
-----
568+
To create an IPC-Enabled memory resource (MR) that is capable of sharing
569+
allocations between processes, specify ``ipc_enabled=True`` in the initializer
570+
option. Sharing an allocation is a two-step procedure that involves
571571
mapping a memory resource and then mapping buffers owned by that resource.
572572
These steps can be accomplished in several ways.
573573
574-
An IPC-enabled memory resource (MR) can allocate memory buffers but cannot
574+
An IPC-enabled memory resource can allocate memory buffers but cannot
575575
receive shared buffers. Mapping an MR to another process creates a "mapped
576576
memory resource" (MMR). An MMR cannot allocate memory buffers and can only
577577
receive shared buffers. MRs and MMRs are both of type

0 commit comments

Comments
 (0)