[MoE] enable all2all fi_one_sided by default (#53311)
Signed-off-by: Artem Perevedentsev <aperevedents@nvidia.com>
This commit is contained in:
@@ -815,6 +815,10 @@ class FlashInferNVLinkOneSidedManager(All2AllManagerBase):
|
||||
comm_backend=CustomCommunicator(self.cpu_group),
|
||||
)
|
||||
|
||||
# Release cached allocator blocks before FlashInfer reserves the
|
||||
# symmetric MNNVL fabric workspace.
|
||||
torch.accelerator.empty_cache()
|
||||
|
||||
self.moe_alltoall = MoeAlltoAll(
|
||||
mapping=self.mapping,
|
||||
max_num_tokens=self.max_num_tokens,
|
||||
|
||||
Reference in New Issue
Block a user