Integrate deep-ep nccl backend #117

	name: windows-x64-gpu
	on:
	push:
	paths:
	- '.github/workflows/windows_x64_gpu.yml'
	- 'src/**'
	- 'CMakeLists.txt'
	- 'cmake/**'
	- 'examples/**'
	- '3rdparty/**'
	- 'tests/csrc/**'
	pull_request:
	paths:
	- '.github/workflows/windows_x64_gpu.yml'
	- 'src/**'
	- 'CMakeLists.txt'
	- 'cmake/**'
	- 'examples/**'
	- '3rdparty/**'
	- 'tests/csrc/**'
	concurrency:
	group: windows-x64-gpu-${{ github.ref }}
	cancel-in-progress: true
	permissions:
	contents: read

	jobs:
	build:
	strategy:
	fail-fast: false
	matrix:
	cudaver: [12.6.2, 12.8.1]
	name: cuda-${{ matrix.cudaver }}
	runs-on: windows-latest
	steps:
	- name: Set git for windows
	run: \|
	git config --global core.longpaths true
	- name: Checkout repository
	uses: actions/checkout@v3
	- name: Set up python
	uses: actions/setup-python@v4
	with:
	python-version: '3.10'
	- name: Install python packages
	run: \|
	pip install build
	- name: Setup CUDA Toolkit
	id: cuda-toolkit
	shell: pwsh
	run: ./builder/windows/setup_cuda.ps1
	env:
	INPUT_CUDA_VERSION: ${{ matrix.cudaver }}
	- name: Build wheel
	run: \|
	python -m build --wheel

Provide feedback