Refactor CPU llama inference code (#728) #47

	# 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 Neural Compressor - Test

	on:
	push:
	branches: [ main ]
	pull_request:
	branches: [ main ]

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

	jobs:
	build:
	strategy:
	fail-fast: false
	matrix:
	python-version: [3.8, 3.9]
	os: [ubuntu-latest]

	runs-on: ${{ matrix.os }}
	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 cmake
	pip install py-cpuinfo
	pip install torch==2.3.0 torchaudio==2.3.0 torchvision==0.18 --index-url https://download.pytorch.org/whl/cpu
	pip install .[neural-compressor,diffusers,tests]
	pip install intel-extension-for-transformers
	pip install peft

	- name: Test with Pytest
	run: \|
	pytest tests/neural_compressor/ --ignore tests/neural_compressor/test_ipex.py --durations=0
	- name: Test IPEX
	run: \|
	pip uninstall -y intel-extension-for-transformers
	pip install intel-extension-for-pytorch==2.3.0
	pytest tests/neural_compressor/test_ipex.py

Provide feedback