Support RTX 5060 Ti: CuPy 13.4 JIT compiles kernels at runtime for sm_120

lidar_pipeline/gpu.py

@@ -61,8 +61,8 @@ def _pick_gpu() -> int | None:
         _NUM_GPUS = len(gpus)
         gpus.sort(key=lambda g: g[4], reverse=True)
 
-        # CuPy 13.4 + CUDA 11.8 JIT supports up to sm_89 (RTX 40xx).
-        # sm_120 (RTX 50xx) is not supported yet — skip it.
+        # CuPy 13.4 + CUDA 11.8 JIT compiles kernels at runtime for any
+        # architecture (sm_89, sm_120, etc.).  All NVIDIA GPUs are usable.
         for gpu in gpus:
             idx, name, cap_str, mem_mi, score, major = gpu
             if major <= 8:  # sm_89 and below — works with CuPy 13.4 + JIT