mirror of
https://github.com/wassname/vllm.git
synced 2026-08-15 12:54:49 +08:00
Add fused top-K softmax kernel for MoE (#2769)
This commit is contained in:
@@ -0,0 +1,7 @@
|
||||
#include "moe_ops.h"
|
||||
|
||||
#include <torch/extension.h>
|
||||
|
||||
PYBIND11_MODULE(TORCH_EXTENSION_NAME, m) {
|
||||
m.def("topk_softmax", &topk_softmax, "Apply topk softmax to the gating outputs.");
|
||||
}
|
||||
Reference in New Issue
Block a user