[AMD] [GLM5] Guard cuda_runtime.h for ROCm in fused_metadata_copy (#29373)

Co-authored-by: Raiden-Makoto <Raiden-Makoto@users.noreply.github.com>

python/sglang/jit_kernel/csrc/elementwise/fused_metadata_copy.cuh

@@ -35,7 +35,11 @@
 #include <tvm/ffi/container/tensor.h>
 
 #include <algorithm>  // for std::min
+#ifndef USE_ROCM
 #include <cuda_runtime.h>
+#else
+#include <hip/hip_runtime.h>
+#endif
 
 // Forward mode enum (must match Python ForwardMode in sglang/srt/layers/attention/dsa_backend.py)
 enum ForwardModeEnum { DECODE = 0, TARGET_VERIFY = 1, DRAFT_EXTEND = 2 };