dharak-cohereandCursor d0e695a91b [Distributed] Support pre-shared ncclUniqueId rendezvous for weight transfer (#53784) ...

Signed-off-by: Dharak Kharod <dharak.kharod@cohere.com>
Co-authored-by: Cursor <cursoragent@cursor.com>

2026-09-01 14:55:57 +08:00

..

__init__.py

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

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

aiter_custom_all_reduce.py

[ROCm][AITER] Directly Implement AITER Custom All-reduce in CudaCommunicator (#46065)

2026-07-06 12:16:32 +00:00

all2all.py

[MoE] enable all2all fi_one_sided by default (#53311)

2026-08-26 17:03:45 +05:00

all_reduce_utils.py

[Perf] Tune FlashInfer all-reduce thresholds for single-node TP8 on SM103 (#53606)

2026-08-26 01:46:56 +00:00

base_device_communicator.py

[Core] Release NCCL communicator memory in sleep mode (#51485)

2026-09-01 14:31:16 +08:00

cpu_communicator.py

[Elastic EP] Async preparation (#47288)

2026-07-28 05:19:13 -07:00

cuda_communicator.py

[Core] Release NCCL communicator memory in sleep mode (#51485)

2026-09-01 14:31:16 +08:00

cuda_wrapper.py

[Bugfix][ROCm] Fix cumem sleep and teardown (#46203)

2026-06-24 02:45:31 +08:00

custom_all_reduce.py

[Model] Support Qwen3.8-Flash-Next (#53896)

2026-08-31 05:57:56 +00:00

flashinfer_all_reduce.py

buffer size insuffient Dspark sd for FlashInfer MNNVL allreduce (#50932)

2026-08-27 11:01:08 -04:00

flashinfer_pcie_ipc_all_reduce.py

[Distributed] Add opt-in FlashInfer PCIe IPC all-reduce backend (#53576)

2026-09-01 03:34:56 +00:00

mnnvl_compat.py

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

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

pynccl_allocator.py

[WideEP] Update NCCL to 2.30.7 to enable DeepEPv2 in the vllm/vllm-openai image (#45321)

2026-07-24 13:00:02 -07:00

pynccl_wrapper.py

[Distributed] Support pre-shared ncclUniqueId rendezvous for weight transfer (#53784)

2026-09-01 14:55:57 +08:00

pynccl.py

[Distributed] Support pre-shared ncclUniqueId rendezvous for weight transfer (#53784)

2026-09-01 14:55:57 +08:00

quick_all_reduce.py

[ROCM] [Communication] Add INT3 quantization method for quickreduce (#45666)

2026-06-25 15:14:15 +00:00

ray_communicator.py

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

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

shm_broadcast.py

[Bugfix] Fix ZMQ port TOCTOU race in shm_broadcast MessageQueue (#50960)

2026-08-07 18:19:02 -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

[Rubin] Enable NVLink all-reduce paths on SM107 (#49647)

2026-07-29 20:53:25 +00:00

xpu_communicator.py

[Elastic EP] Async preparation (#47288)

2026-07-28 05:19:13 -07:00