[2/n] Migrate per_token_group_quant to torch stable ABI (#36058)

Signed-off-by: Mikayla Gawarecki <mikaylagawarecki@gmail.com>

csrc/libtorch_stable/torch_utils.h

@@ -1,11 +1,13 @@
 #pragma once
 
 #include <torch/csrc/inductor/aoti_torch/c/shim.h>
+#include <torch/headeronly/util/shim_utils.h>
+
 #include <cuda_runtime.h>
 
 // Utility to get the current CUDA stream for a given device using stable APIs.
 // Returns a cudaStream_t for use in kernel launches.
-inline cudaStream_t get_current_cuda_stream(int32_t device_index) {
+inline cudaStream_t get_current_cuda_stream(int32_t device_index = -1) {
   void* stream_ptr = nullptr;
   TORCH_ERROR_CODE_CHECK(
       aoti_torch_get_current_cuda_stream(device_index, &stream_ptr));