[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:
co-authored by
mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
aoshen02
parent
4bb804cc5b
commit
b6d2b4fc25
@@ -9,7 +9,9 @@ from vllm.config.utils import config
|
||||
class WeightTransferConfig:
|
||||
"""Configuration for weight transfer during RL training."""
|
||||
|
||||
backend: Literal["nccl", "ipc", "sparse_nccl", "sharded_rdt"] | str = "nccl"
|
||||
backend: Literal["nccl", "ipc", "sparse_nccl", "sharded_rdt", "nccl_m2n"] | str = (
|
||||
"nccl"
|
||||
)
|
||||
"""The backend to use for weight transfer. Validated against the
|
||||
`WeightTransferEngineFactory` registry at engine creation time.
|
||||
"""
|
||||
|
||||
Reference in New Issue
Block a user