Quantization support for CausalVisualLMs #3950

	# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
	# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
	name: Intel IPEX - Test

	on:
	push:
	branches:
	- main
	- v*-release
	pull_request:
	branches:
	- main

	concurrency:
	group: ${{ github.workflow }}-${{ github.head_ref \|\| github.run_id }}
	cancel-in-progress: true

	jobs:
	build:
	runs-on: ubuntu-latest
	strategy:
	fail-fast: false
	matrix:
	python-version: ["3.9"]
	transformers-version: ["4.39.0", "4.44.*"]
	ipex-version: ["2.2.0", "2.3.*"]
	include:
	- python-version: "3.10"
	transformers-version: "4.39.0"
	ipex-version: "2.2.0"

	steps:
	- uses: actions/checkout@v2
	- name: Setup Python ${{ matrix.python-version }}
	uses: actions/setup-python@v2
	with:
	python-version: ${{ matrix.python-version }}
	- name: Install dependencies
	run: \|
	python -m pip install --upgrade pip
	pip install torch==${{ matrix.ipex-version }} --extra-index-url https://download.pytorch.org/whl/cpu
	pip install intel_extension_for_pytorch==${{ matrix.ipex-version }}
	pip install Pillow parameterized
	pip install transformers[testing]==${{ matrix.transformers-version }}
	pip install .[ipex]

	- if: ${{ matrix.ipex-version == '2.2.0' }}
	run: pip install numpy==1.*

	- name: Test with Pytest
	run: \|
	pytest tests/ipex/

Provide feedback