NVIDIA/cuCascade

View on GitHub

GPU Memory Reservation Library

Stars: 59
Forks: 35
Open beginner issues: 0
Indexed issues: 12
Avg merge: 17h 38m
Merged PRs (30d): 3

Dominant language: C++
License: Apache-2.0
Last GitHub push: Sep 17, 2026
Latest indexed: Sep 19, 2026
Contributing guide: No contributing guide
Code of conduct: No code of conduct
Beginner labels: No beginner labels indexed

Beginner friendly Everything

Open All

12 open issues indexed

Expose safe per-pool peer access for configured GPU pairs Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

NVIDIA/cuCascade#199 · Opened Sep 17, 2026
cuCascade Topology Detection Breakage Open

Difficulty 4/5 3-5 days Newbie friendliness 20/100

NVIDIA/cuCascade#194 · Opened Aug 26, 2026
[Story] Memory-resources-like reservations Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

NVIDIA/cuCascade#193 · Opened Aug 25, 2026
Add the ability for a memory space to have more than one allocator. Open

Difficulty 5/5 Over a week Newbie friendliness 30/100

NVIDIA/cuCascade#159 · Opened Jul 8, 2026
Make reservation-aware converter overloads honor GPU and DISK target reservations Open

Difficulty 3/5 1-2 days Newbie friendliness 52/100

NVIDIA/cuCascade#155 · Opened Jul 1, 2026
Make fixed size host block allocations cuda stream aware Open

rapidsmpf request

Difficulty 5/5 Over a week Newbie friendliness 42/100

NVIDIA/cuCascade#93 · Opened Mar 25, 2026
`fixed_size_host_memory_resource` could be movable Open

rapidsmpf request

Difficulty 3/5 1-2 days Newbie friendliness 45/100

NVIDIA/cuCascade#48 · Opened Feb 11, 2026
Make some kind of scheduling policy for satisfying reservations Open

feature request improvement

Difficulty 5/5 Over a week Newbie friendliness 35/100

NVIDIA/cuCascade#20 · 1 comment · Opened Jan 8, 2026
create data_repr to be the same as idata_repr but without a memoryspace Open

feature request

Difficulty 4/5 3-5 days Newbie friendliness 48/100

NVIDIA/cuCascade#18 · 1 comment · Opened Jan 7, 2026
Should we have multiple converters between the same idata_representations Open

feature request improvement

Difficulty 5/5 Over a week Newbie friendliness 25/100

NVIDIA/cuCascade#17 · Opened Jan 7, 2026
Converters should include destination output size and temporary allocations that need to be allocated for performing allocations Open

feature request improvement

Difficulty 5/5 Over a week Newbie friendliness 25/100

NVIDIA/cuCascade#16 · Opened Jan 7, 2026
Create a reserve and callback method Open

rapidsmpf request

Difficulty 5/5 Over a week Newbie friendliness 25/100

NVIDIA/cuCascade#13 · Opened Jan 7, 2026

NVIDIA/cuCascade

Get new issues in your inbox