[feat] FlashInfer CuteDSL MegaMoE integration (#54049)
Signed-off-by: jdebache <jdebache@nvidia.com>
This commit is contained in:
@@ -1068,6 +1068,12 @@ class FusedMoEParallelConfig:
|
||||
and self.all2all_backend == "allgather_reducescatter"
|
||||
)
|
||||
|
||||
@property
|
||||
def use_passthrough_all2all(self):
|
||||
# Not gated on use_all2all_kernels: the experts dispatch and combine
|
||||
# internally in every EP topology, including TP-only.
|
||||
return self.all2all_backend == "passthrough"
|
||||
|
||||
@property
|
||||
def use_mori_kernels(self):
|
||||
return self.use_all2all_kernels and self.all2all_backend in (
|
||||
@@ -1530,6 +1536,10 @@ class FusedMoEConfig:
|
||||
def use_deepep_ll_kernels(self):
|
||||
return self.moe_parallel_config.use_deepep_ll_kernels
|
||||
|
||||
@property
|
||||
def use_passthrough_all2all(self):
|
||||
return self.moe_parallel_config.use_passthrough_all2all
|
||||
|
||||
@property
|
||||
def use_mori_kernels(self):
|
||||
return self.moe_parallel_config.use_mori_kernels
|
||||
|
||||
Reference in New Issue
Block a user