[Kernels] Overlap shared experts with send/recv (#23273)

Signed-off-by: Bill Nell <bnell@redhat.com>
This commit is contained in:
bnellnm
2025-09-03 12:35:18 -04:00
committed by GitHub
parent fa4311d85f
commit e9b92dcd89
32 changed files with 885 additions and 227 deletions
@@ -491,7 +491,7 @@ class ModelOptFp8MoEMethod(FusedMoEMethodBase):
expert_load_view: Optional[torch.Tensor] = None,
logical_to_physical_map: Optional[torch.Tensor] = None,
logical_replica_count: Optional[torch.Tensor] = None,
) -> torch.Tensor:
) -> Union[torch.Tensor, tuple[torch.Tensor, torch.Tensor]]:
if enable_eplb:
raise NotImplementedError(
"EPLB not supported for `ModelOptFp8MoEMethod` yet.")
@@ -1366,7 +1366,7 @@ class ModelOptNvFp4FusedMoE(FusedMoEMethodBase):
expert_load_view: Optional[torch.Tensor] = None,
logical_to_physical_map: Optional[torch.Tensor] = None,
logical_replica_count: Optional[torch.Tensor] = None,
):
) -> Union[torch.Tensor, tuple[torch.Tensor, torch.Tensor]]:
if enable_eplb:
raise NotImplementedError(
"EPLB not supported for `ModelOptNvFp4FusedMoE` yet.")