Fadi Arafeh 2aab9acf48 [CPU][BugFix] Fix inter-node pipeline parallel (#40150) ...

Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>

2026-04-20 17:21:12 +08:00

..

__init__.py

[Core][Refactor] move parallel_utils into vllm/distributed (#3950)

2024-04-10 15:33:30 -07:00

all2all.py

[ROCm] Enable DeepEP ROCm as all2allbackend for AMD GPUs. (#34692)

2026-03-21 00:32:31 -07:00

all_reduce_utils.py

replace cuda_device_count_stateless() to current_platform.device_count() (#37841)

2026-03-31 22:32:54 +08:00

base_device_communicator.py

[1/N] Elastic EP Milestone 2 (#34861)

2026-02-28 04:46:42 +00:00

cpu_communicator.py

[CPU][BugFix] Fix inter-node pipeline parallel (#40150)

2026-04-20 17:21:12 +08:00

cuda_communicator.py

elastic_ep: Fix issues with repeated scale up/down cycles (#37131)

2026-03-20 23:13:02 +00:00

cuda_wrapper.py

refactor: find_loaded_library (#31866)

2026-01-07 06:42:20 +00:00

custom_all_reduce.py

replace cuda_device_count_stateless() to current_platform.device_count() (#37841)

2026-03-31 22:32:54 +08:00

flashinfer_all_reduce.py

Fix multi-node allreduce fusion (#38136)

2026-03-26 20:24:36 +00:00

mnnvl_compat.py

[Kernel] Add FlashInfer MoE A2A Kernel (#36022)

2026-03-15 23:45:32 -07:00

pynccl_allocator.py

[Hardware] Replace torch.cuda.device_count/current_device/set_device API (#36145)

2026-03-12 07:57:47 -07:00

pynccl_wrapper.py

[EPLB] Add alternative communication for EPLB weight exchange (#33176)

2026-03-31 08:17:12 -04:00

pynccl.py

elastic_ep: Fix issues with repeated scale up/down cycles (#37131)

2026-03-20 23:13:02 +00:00

quick_all_reduce.py

replace cuda_device_count_stateless() to current_platform.device_count() (#37841)

2026-03-31 22:32:54 +08:00

ray_communicator.py

[Misc] Avoid "PyTorch non-writable tensors" warning in RayPPCommunicator (#27443)

2025-10-24 14:53:09 +08:00

shm_broadcast.py

[CI] Bump mypy version to 1.19.1 (#36104)

2026-03-10 09:18:28 -07:00

shm_object_storage.py

[CI] Bump mypy version to 1.19.1 (#36104)

2026-03-10 09:18:28 -07:00

symm_mem.py

[Bugfix] Register VLLM_BATCH_INVARIANT in envs.py to fix spurious unknown env var warning (#35007)

2026-03-23 18:31:14 -04:00

xpu_communicator.py

[XPU] fix all_reduce all-zero accuracy issue under torch.compile (#39844)

2026-04-18 02:33:07 +00:00