feat: add some misc CUDA kernels #2688

	name: Header-only Tests

	on:
	pull_request:
	workflow_dispatch:


	concurrency:
	group: header-only-test-${{ github.head_ref }}
	cancel-in-progress: true

	jobs:
	test:
	name: "Run Tests"
	strategy:
	matrix:
	os: [ubuntu-latest, macos-13, windows-latest]
	runs-on: ${{ matrix.os }}

	steps:
	- uses: actions/checkout@v4
	with:
	submodules: true

	- name: Run CMake
	run: \|
	cmake -B build -S header-only -DCMAKE_RUNTIME_OUTPUT_DIRECTORY=bin -DCMAKE_BUILD_TYPE=Debug -DBUILD_TESTS=ON
	cmake --build build/

	- name: Run tests
	run: \|
	import os
	import pathlib
	import subprocess
	for path in pathlib.Path("build/tests/bin").glob("test_*"):
	if path.is_file():
	print(f"Running {path.name}", flush=True)
	print("::group::Test output", flush=True)
	subprocess.run([path], check=True)
	print("::endgroup::", flush=True)
	shell: python3 {0}

Provide feedback