[Kernel][Performance] Fuse float cast and renormalize to topk softmax kernel (#26717)
Signed-off-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com> Signed-off-by: izhuhaoran <izhuhaoran@qq.com>
This commit is contained in:
+2
-1
@@ -1850,9 +1850,10 @@ def topk_softmax(
|
||||
topk_ids: torch.Tensor,
|
||||
token_expert_indices: torch.Tensor,
|
||||
gating_output: torch.Tensor,
|
||||
renormalize: bool = False,
|
||||
) -> None:
|
||||
torch.ops._moe_C.topk_softmax(
|
||||
topk_weights, topk_ids, token_expert_indices, gating_output
|
||||
topk_weights, topk_ids, token_expert_indices, gating_output, renormalize
|
||||
)
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user