bnellnm 18f6bf5a21 [MoE Refactor] Add sequence parallel tests to test_moe_layer.py (#41299) ...

Signed-off-by: Bill Nell <bnell@redhat.com>

2026-05-12 21:52:19 -04:00

..

__init__.py

…

all2all.py

[MoE Refactor] Add sequence parallel tests to test_moe_layer.py (#41299)

2026-05-12 21:52:19 -04:00

all_reduce_utils.py

…

base_device_communicator.py

[MoE Refactor] Remove SharedFusedMoE class (#35782)

2026-04-21 18:12:12 -04:00

cpu_communicator.py

[WideEP] Remove naive all2all. Use allgather_reducescatter instead (#33728)

2026-04-20 17:53:55 +00:00

cuda_communicator.py

[MoE Refactor] Add sequence parallel tests to test_moe_layer.py (#41299)

2026-05-12 21:52:19 -04:00

cuda_wrapper.py

…

custom_all_reduce.py

…

flashinfer_all_reduce.py

…

mnnvl_compat.py

…

pynccl_allocator.py

…

pynccl_wrapper.py

[BugFix] Prevent orphaned process on NCCL destroy (#39846)

2026-05-11 15:25:26 -04:00

pynccl.py

[BugFix] Prevent orphaned process on NCCL destroy (#39846)

2026-05-11 15:25:26 -04:00

quick_all_reduce.py

…

ray_communicator.py

…

shm_broadcast.py

Add VLLM_USE_SPINLOOP_EXT to use more efficient busy polling (#36517)

2026-05-11 16:11:49 -07:00

shm_object_storage.py

…

symm_mem.py

…

xpu_communicator.py

[XPU] Implement out-of-place all-reduce functionality (#41808)

2026-05-07 05:58:05 -07:00