Binyang Li 7c390fffd6 Expose NVLS multicast granularity option for GpuBuffer (#815) ...

Add a public Granularity enum (MultiCastMinimum, MultiCastRecommended)
and let GpuBuffer choose the NVLS multicast allocation granularity via a
constructor argument, defaulting to MultiCastMinimum to minimize memory
usage. Expose the same option through the C++ and Python (nanobind)
APIs.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

2026-06-04 13:16:18 -07:00

..

ext

Adjusting Torch Integration Example (#779)

2026-04-10 13:57:14 -07:00

algorithm.cpp

Support E4M3B15 datatype (#765)

2026-04-07 13:37:02 -07:00

CMakeLists.txt

Support python wheel build (#787)

2026-04-16 21:24:45 -07:00

core_py.cpp

Fix FP8 ROCm build/test issues and dtype naming (#792)

2026-04-28 15:02:22 -07:00

env_py.cpp

Add MSCCLPP_IB_GID_INDEX env (#780)

2026-04-13 09:59:42 -07:00

error_py.cpp

Fix cpplint error in main branch (#740)

2026-02-05 09:25:12 -08:00

executor_py.cpp

Address comments for PR #692 (#733)

2026-02-03 10:13:20 -08:00

fifo_py.cpp

Address comments for PR #692 (#733)

2026-02-03 10:13:20 -08:00

gpu_utils_py.cpp

Expose NVLS multicast granularity option for GpuBuffer (#815)

2026-06-04 13:16:18 -07:00

memory_channel_py.cpp

Address comments for PR #692 (#733)

2026-02-03 10:13:20 -08:00

npkit_py.cpp

Fix cpplint error in main branch (#740)

2026-02-05 09:25:12 -08:00

numa_py.cpp

Fix cpplint error in main branch (#740)

2026-02-05 09:25:12 -08:00

port_channel_py.cpp

Address comments for PR #692 (#733)

2026-02-03 10:13:20 -08:00

semaphore_py.cpp

Use PTX red for D2D semaphore signal (#768)

2026-03-31 15:34:43 -07:00

switch_channel_py.cpp

Address comments for PR #692 (#733)

2026-02-03 10:13:20 -08:00

utils_py.cpp

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

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