Optimize `_length_per_key_from_stride_per_key` with segment sum csr when appropriate #3951

	name: Build Dynamic Embedding Wheels

	on:
	workflow_dispatch:
	pull_request:
	branches:
	- main
	push:
	branches:
	- main
	release:
	types:
	- published

	jobs:
	build_wheels:
	name: Wheels on ${{ matrix.os }}/${{ matrix.pyver }}/cu${{ matrix.cuver }}
	runs-on: ${{ matrix.os }}
	strategy:
	fail-fast: false
	matrix:
	os: [ ubuntu-latest ]
	pyver: [ cp38, cp39, cp310 ]
	cuver: [ "11.8" ]

	steps:
	-
	name: Check disk space
	run: df . -h

	- name: Remove unnecessary files
	run: \|
	sudo rm -rf /usr/share/dotnet
	sudo rm -rf "$AGENT_TOOLSDIRECTORY"

	-
	name: Check disk space
	run: df . -h

	- uses: actions/checkout@v3
	with:
	submodules: recursive

	- uses: pypa/[email protected]
	with:
	package-dir: contrib/dynamic_embedding
	env:
	CIBW_BEFORE_BUILD: "env CUDA_VERSION=${{ matrix.cuver }} contrib/dynamic_embedding/tools/before_linux_build.sh"
	CIBW_BUILD: "${{ matrix.pyver }}-manylinux_x86_64"
	CIBW_REPAIR_WHEEL_COMMAND: "env CUDA_VERSION=${{ matrix.cuver }} contrib/dynamic_embedding/tools/repair_wheel.sh {wheel} {dest_dir}"

	- name: Verify clean directory
	run: git diff --exit-code
	shell: bash

	- name: Upload wheels
	uses: actions/upload-artifact@v3
	with:
	path: wheelhouse/*.whl

Provide feedback