[Perf][MoE] Write FlashInfer combine into final output (#47156)
Signed-off-by: snordmann <snordmann@nvidia.com> Co-authored-by: Codex <codex@openai.com>
This commit is contained in:
+2
-2
@@ -161,8 +161,8 @@ class FlashInferNVLinkOneSidedPrepareAndFinalize(mk.FusedMoEPrepareAndFinalizeMo
|
||||
ep_size, self.runtime_max_tokens_per_rank, hidden_size
|
||||
)
|
||||
|
||||
combined_output = self.all2all_manager.moe_alltoall.combine( # type: ignore[attr-defined]
|
||||
self.all2all_manager.combine_into( # type: ignore[attr-defined]
|
||||
payload=fused_expert_output,
|
||||
runtime_max_tokens_per_rank=self.runtime_max_tokens_per_rank,
|
||||
output=output,
|
||||
)
|
||||
output.copy_(combined_output)
|
||||
|
||||
Reference in New Issue
Block a user