fix(build): repair the macOS conda build and the CUDA wheel toolchain

pixi.toml

@@ -104,6 +104,12 @@ mkl-devel = "*"
 # itself is deliberately absent, as it is from the release list: it drags in
 # cudensitymat, cupauliprop and custabilizer, none of which cytnx links.
 nvidia-cuda-nvcc = "~=13.3.73"
+# Named although nvidia-cuda-nvcc already depends on them: it does so without
+# version bounds, which lets a re-resolve pick a newer CUDA minor version for
+# cicc (nvidia-nvvm) than for ptxas (nvidia-cuda-nvcc), and ptxas rejects a
+# PTX ISA newer than its own. Must match nvidia-cuda-nvcc above.
+nvidia-nvvm = "~=13.3.73"
+nvidia-cuda-crt = "~=13.3.73"
 nvidia-cuda-cccl = "~=13.3.3.4.1"
 nvidia-cuda-runtime = "~=13.3.29"
 nvidia-cublas = "~=13.6.0.2"

src/utils/vec_intersect.cpp

@@ -1,6 +1,7 @@
 #include "utils/vec_intersect.hpp"
 #include "utils/vec2d_col_sort.hpp"
 #include <algorithm>
+#include <iterator>
 #include <vector>
 namespace cytnx {
 

tools/prepare_cuda_release.py

@@ -87,6 +87,13 @@
 # dropped here since this only ever runs inside the Linux manylinux container.
 CUDA_BUILD_TOOLCHAIN = [
     "nvidia-cuda-nvcc ~=13.3.73",
+    # Named although nvidia-cuda-nvcc already depends on them: it does so
+    # without version bounds, which lets pip resolve a newer CUDA minor
+    # version for cicc (nvidia-nvvm) than for ptxas (nvidia-cuda-nvcc), and
+    # ptxas rejects a PTX ISA newer than its own. Must match the
+    # nvidia-cuda-nvcc version above.
+    "nvidia-nvvm ~=13.3.73",
+    "nvidia-cuda-crt ~=13.3.73",
     "nvidia-cuda-cccl ~=13.3.3.4.1",
 ] + [
     spec.split(";")[0].strip() for spec in CUDA_RUNTIME_DEPENDENCIES