[CCCL] 瘦身 + 补全: 移除 cudax/python/libcudacxx-tests 冗余文件, 新增 c2h 测试助手 + cmake 构建系统 + 8 个 CUDA thrust examples

变更摘要:
- 删除: cudax/ (783 files, 7.2M) — 实验性组件，竞赛不需要
- 删除: python/ (226 files, 2.0M) — Python 绑定，竞赛不需要
- 删除: libcudacxx/{test,benchmarks,codegen,cmake,share} (4432 files, 31M)
  保留: libcudacxx/include/ (1463 headers, cuda::std 编译依赖)
- 新增: c2h/ (27 files) — CUB Catch2 测试辅助头文件，编译 243 个测试必需
- 新增: cmake/ (29 files) — CCCL 原生 CMake 构建系统
- 新增: thrust/examples/cuda/ (7 files) + cpp_integration/ (1 file)
  async_reduce, custom_temporary_allocation, explicit_cuda_stream,
  global_device_vector, range_view, unwrap_pointer, wrap_pointer, device

结果: cccl_upstream 从 74M→35M (瘦身 53%), 核心内容 100% 保留:
  27/27 tuning headers, 78 benchmarks, 243 tests,
  60 thrust examples, 18 CUB examples, 全部编译头文件

cccl_upstream/python/cuda_cccl/cuda/cccl/headers/__init__.py

@@ -1,7 +0,0 @@
-# Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES. ALL RIGHTS RESERVED.
-#
-# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
-
-from .include_paths import get_include_paths
-
-__all__ = ["__version__", "get_include_paths"]

cccl_upstream/python/cuda_cccl/cuda/cccl/headers/include/__init__.py

@@ -1 +0,0 @@
-# Intentionally empty

cccl_upstream/python/cuda_cccl/cuda/cccl/headers/include_paths.py

@@ -1,51 +0,0 @@
-# Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES. ALL RIGHTS RESERVED.
-#
-# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
-
-import sys
-from dataclasses import dataclass
-from functools import lru_cache
-from importlib.resources import as_file, files
-from pathlib import Path
-from typing import Optional
-
-# type: ignore[import-not-found]
-from cuda.pathfinder import find_nvidia_header_directory
-
-
-@dataclass
-class IncludePaths:
-    cuda: Optional[Path]
-    libcudacxx: Optional[Path]
-    cub: Optional[Path]
-    thrust: Optional[Path]
-
-    def as_tuple(self):
-        # Note: higher-level ... lower-level order:
-        return (self.thrust, self.cub, self.libcudacxx, self.cuda)
-
-
-@lru_cache()
-def get_include_paths(probe_file: str = "cub/version.cuh") -> IncludePaths:
-    cuda_incl = find_nvidia_header_directory("cudart")
-    if cuda_incl is None:
-        raise RuntimeError("Unable to locate CUDA include directory.")
-
-    with as_file(files("cuda.cccl.headers.include")) as f:
-        cccl_incl = Path(f)
-
-    probe_file_path = Path(probe_file)
-    if not (cccl_incl / probe_file_path).exists():
-        for sp in sys.path:
-            cccl_incl = Path(sp).resolve() / "cuda" / "cccl" / "headers" / "include"
-            if (cccl_incl / probe_file_path).exists():
-                break
-        else:
-            raise RuntimeError("Unable to locate CCCL include directory.")
-
-    return IncludePaths(
-        cuda=cuda_incl,
-        libcudacxx=cccl_incl,
-        cub=cccl_incl,
-        thrust=cccl_incl,
-    )