[2/N] Elastic EP Milestone 2: Integrating NIXL-EP (#35627)
Signed-off-by: Itay Alroy <ialroy@nvidia.com> Co-authored-by: Yongji Wu <wuyongji317@gmail.com> Co-authored-by: Ron Tourgeman <rtourgeman@nvidia.com>
This commit is contained in:
co-authored by
Yongji Wu
Ron Tourgeman
parent
82f836d976
commit
d5af196c18
@@ -177,10 +177,11 @@ def determine_expert_placement_strategy(
|
||||
if (
|
||||
moe_parallel_config.use_all2all_kernels
|
||||
and not moe_parallel_config.use_deepep_ll_kernels
|
||||
and not moe_parallel_config.use_nixl_ep_kernels
|
||||
):
|
||||
logger.warning(
|
||||
"Round-robin expert placement currently only supports "
|
||||
"the DeepEP low-latency backend, but '%s' was configured. "
|
||||
"the DeepEP low-latency or NIXL EP backend, but '%s' was configured. "
|
||||
"Falling back to linear expert placement.",
|
||||
moe_parallel_config.all2all_backend,
|
||||
)
|
||||
@@ -745,10 +746,10 @@ class FusedMoE(CustomOp):
|
||||
self,
|
||||
) -> tuple[torch.Tensor, torch.Tensor, torch.Tensor] | None:
|
||||
# Currently routing_tables only needed for round-robin expert placement
|
||||
# with DeepEP-ll all2all backend.
|
||||
if (
|
||||
self.expert_placement_strategy != "round_robin"
|
||||
or not self.moe_parallel_config.use_deepep_ll_kernels
|
||||
# with DeepEP-ll or NIXL EP all2all backends.
|
||||
if self.expert_placement_strategy != "round_robin" or (
|
||||
not self.moe_parallel_config.use_deepep_ll_kernels
|
||||
and not self.moe_parallel_config.use_nixl_ep_kernels
|
||||
):
|
||||
return None
|
||||
|
||||
|
||||
Reference in New Issue
Block a user