Binyang Li eda74a7f29 Add handle cache for AMD platform (#698) ...

Introduce handle cache for AMD platform.
Avoid reaching handle limitation if we open too much IPC handles

For nvidia, we don't need this feature since nvidia will count the
handle reference internally and reuse the same handle if already be
opened

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Binyang2014 <9415966+Binyang2014@users.noreply.github.com>
Co-authored-by: Changho Hwang <changhohwang@microsoft.com>

2025-12-21 18:39:12 -08:00

..

_cpp

Make IB more configurable (#703)

2025-12-18 13:21:07 -08:00

configs

Add multi-nodes example & update doc (#455)

2025-01-31 17:52:15 -08:00

__init__.py

Pytest (#162)

2023-09-01 21:22:11 +08:00

CMakeLists.txt

Fix bootstrapping mechanism (#278)

2024-03-27 10:24:24 +08:00

conftest.py

Add handle cache for AMD platform (#698)

2025-12-21 18:39:12 -08:00

d2d_semaphore_test.cu

Renaming channels (#436)

2025-01-24 14:25:31 -08:00

executor_test_verifier.cu

AlltoAll Test Support (#606)

2025-08-15 16:00:41 -07:00

executor_test.py

Integrate MSCCL++ DSL to torch workload (#620)

2025-10-29 15:39:00 -07:00

fifo_test.cu

Atomic for semaphores instead of fences (#188)

2023-10-13 18:57:08 +08:00

h2d_semaphore_test.cu

Atomic for semaphores instead of fences (#188)

2023-10-13 18:57:08 +08:00

memory_channel_test.cu

Revised MemoryChannel interfaces (#508)

2025-04-25 00:02:56 +00:00

mscclpp_mpi.py

Add handle cache for AMD platform (#698)

2025-12-21 18:39:12 -08:00

nvls_test.cu

Revise NVLS interface (#458)

2025-07-12 00:33:03 +00:00

port_channel_test.cu

Revised MemoryChannel interfaces (#508)

2025-04-25 00:02:56 +00:00

proxy_test.cu

Atomic for semaphores instead of fences (#188)

2023-10-13 18:57:08 +08:00

test_generate_mscclpp_lang_result.py

Merge mscclpp-lang to mscclpp project (#442)

2025-01-22 09:47:37 -08:00

test_mscclpp.py

Fix Python bindings and tests (#690)

2025-11-21 12:53:12 -08:00