[ModelBash][DSV3] Add TRTLLM DSV3 Router GEMM kernel (6% B1 Speedup) (#34302)

Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>

csrc/moe/torch_bindings.cpp

@@ -124,6 +124,10 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, m) {
       "routed_scaling_factor, Tensor bias, int scoring_func) -> (Tensor, "
       "Tensor)");
   m.impl("grouped_topk", torch::kCUDA, &grouped_topk);
+
+  // DeepSeek V3 optimized router GEMM for SM90+
+  m.def("dsv3_router_gemm(Tensor! output, Tensor mat_a, Tensor mat_b) -> ()");
+  m.impl("dsv3_router_gemm", torch::kCUDA, &dsv3_router_gemm);
 #endif
 }