[Kernels][DP/EP] Optimize Silu Kernel for R1 (#24054)

Signed-off-by: elvircrn <elvircrn@gmail.com>

csrc/torch_bindings.cpp

@@ -32,6 +32,13 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, ops) {
   #define stride_tag
 #endif
 
+  ops.def(
+      "silu_mul_fp8_quant_deep_gemm_cuda(Tensor input, Tensor counts, Tensor! "
+      "y_q, Tensor! y_s, int group_size, "
+      "bool use_ue8m0, int num_parallel_tokens) -> ()");
+  ops.impl("silu_mul_fp8_quant_deep_gemm_cuda", torch::kCUDA,
+           &silu_mul_fp8_quant_deep_gemm_cuda);
+
   ops.def("weak_ref_tensor(Tensor input) -> Tensor");
   ops.impl("weak_ref_tensor", torch::kCUDA, &weak_ref_tensor);