[RL] Add sharding-aware NCCL M2N weight transfer (#51520)

Signed-off-by: Ke Wen <kwen@nvidia.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
This commit is contained in:
Ke Wen
2026-09-26 01:38:53 +00:00
committed by GitHub
co-authored by mergify[bot] <37929162+mergify[bot]@users.noreply.github.com> aoshen02
parent 4bb804cc5b
commit b6d2b4fc25
13 changed files with 2812 additions and 6 deletions
@@ -243,6 +243,12 @@ WeightTransferEngineFactory.register_engine(
"ShardedRDTWeightTransferEngine",
)
WeightTransferEngineFactory.register_engine(
"nccl_m2n",
"vllm.distributed.weight_transfer.m2n_engine",
"M2NWeightTransferEngine",
)
# Trainer-side engines, parallel to the worker registry above.
WeightTransferTrainerFactory.register_engine(
@@ -268,3 +274,9 @@ WeightTransferTrainerFactory.register_engine(
"vllm.distributed.weight_transfer.sharded_rdt_trainer",
"ShardedRDTTrainerWeightTransferEngine",
)
WeightTransferTrainerFactory.register_engine(
"nccl_m2n",
"vllm.distributed.weight_transfer.m2n_trainer",
"M2NTrainerWeightTransferEngine",
)