[Kernel] Add topk_sigmoid kernel (#31246)

Signed-off-by: Xin Yang <xyangx@amazon.com>
This commit is contained in:
Xin Yang
2026-01-21 22:49:51 +00:00
committed by GitHub
parent e675dda67b
commit 63227accf5
13 changed files with 725 additions and 126 deletions
+9 -1
View File
@@ -5,9 +5,17 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, m) {
// Apply topk softmax to the gating outputs.
m.def(
"topk_softmax(Tensor! topk_weights, Tensor! topk_indices, Tensor! "
"token_expert_indices, Tensor gating_output, bool renormalize) -> ()");
"token_expert_indices, Tensor gating_output, bool renormalize, Tensor? "
"bias) -> ()");
m.impl("topk_softmax", torch::kCUDA, &topk_softmax);
// Apply topk sigmoid to the gating outputs.
m.def(
"topk_sigmoid(Tensor! topk_weights, Tensor! topk_indices, Tensor! "
"token_expert_indices, Tensor gating_output, bool renormalize, Tensor? "
"bias) -> ()");
m.impl("topk_sigmoid", torch::kCUDA, &topk_sigmoid);
// Calculate the result of moe by summing up the partial results
// from all selected experts.
m.def("moe_sum(Tensor input, Tensor! output) -> ()");