Woosuk Kwonandsnordmann 953bba488d [PERF] Extend NCCL symmetric memory to AllGather and ReduceScatter (#46703) ...

Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: snordmann <snordmann@nvidia.com>

2026-06-30 11:38:18 -07:00

..

device_communicators

[PERF] Extend NCCL symmetric memory to AllGather and ReduceScatter (#46703)

2026-06-30 11:38:18 -07:00

ec_transfer

[EC Connector] Non blocking EC Connector lookup (#41627)

2026-06-02 08:48:25 +00:00

elastic_ep

[EPLB] Mask padding in EPLB load recording (#38128)

2026-06-28 19:43:58 -07:00

eplb

[Platform] Replace torch.cuda.Event with torch.Event (#47140)

2026-06-30 08:39:59 -07:00

kv_transfer

[Platform] Replace torch.cuda.Event with torch.Event (#47140)

2026-06-30 08:39:59 -07:00

weight_transfer

[Frontend][Core] Add sparse NCCL weight transfer support for in-place updates (#40096)

2026-06-01 15:37:30 -04:00

__init__.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

communication_op.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

kv_events.py

[KV Events] Switch event structs from array to map encoding (#42892)

2026-06-09 11:39:52 +00:00

nixl_utils.py

[EPLB] Change default EPLB communicator (#43110)

2026-05-22 09:43:27 -04:00

parallel_state.py

Stop setting CUDA_VISIBLE_DEVICES internally in vLLM, add device_ids arg (#45026)

2026-06-20 13:38:10 -07:00

stateless_coordinator.py

Stop setting CUDA_VISIBLE_DEVICES internally in vLLM, add device_ids arg (#45026)

2026-06-20 13:38:10 -07:00

utils.py

[Bugfix][Quant] Raise actionable error instead of bare assert for group-size/TP mismatch (#46230) (#46236)

2026-06-30 14:57:14 +00:00