Optimum neuron LLM inference cache builder #20
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Optimum neuron LLM inference cache builder | |
| on: | |
| workflow_dispatch: | |
| schedule: | |
| # Schedule the workflow to run every day at midnight UTC | |
| - cron: '0 0 * * *' | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }} | |
| jobs: | |
| cache: | |
| name: Create optimum-neuron inference cache | |
| runs-on: | |
| group: aws-inf2-48xlarge | |
| env: | |
| AWS_REGION: us-east-1 | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| config: [ | |
| gpt2, | |
| llama3-8b, | |
| llama3-70b, | |
| llama2-7b-13b, | |
| llama2-70b, | |
| mistral, | |
| llama-variants, | |
| mistral-variants, | |
| mixtral | |
| ] | |
| steps: | |
| - name: Install Neuron runtime | |
| run: | | |
| . /etc/os-release | |
| sudo tee /etc/apt/sources.list.d/neuron.list > /dev/null <<EOF | |
| deb https://apt.repos.neuron.amazonaws.com ${VERSION_CODENAME} main | |
| EOF | |
| wget -qO - https://apt.repos.neuron.amazonaws.com/GPG-PUB-KEY-AMAZON-AWS-NEURON.PUB | sudo apt-key add - | |
| sudo apt-get update -y | |
| sudo apt-get install aws-neuronx-tools=2.19.0.0 aws-neuronx-runtime-lib=2.22.14.0-6e27b8d5b aws-neuronx-collectives=2.22.26.0-17a033bc8 -y | |
| export PATH=/opt/aws/neuron/bin:$PATH | |
| - name: Checkout | |
| uses: actions/checkout@v4 | |
| - name: Install python and create venv | |
| run: | | |
| sudo apt install python3-venv python3-dev -y | |
| python3 -m venv aws_neuron_venv_pytorch | |
| source aws_neuron_venv_pytorch/bin/activate | |
| python -m pip install -U pip | |
| python -m pip config set global.extra-index-url https://pip.repos.neuron.amazonaws.com | |
| - name: Install optimum neuron | |
| run: | | |
| source aws_neuron_venv_pytorch/bin/activate | |
| python -m pip install .[neuronx] | |
| - name: Create cache for ${{matrix.config}} models | |
| run: | | |
| source aws_neuron_venv_pytorch/bin/activate | |
| config_prefix_url=https://huggingface.co/aws-neuron/optimum-neuron-cache/raw/main/inference-cache-config | |
| HF_TOKEN=${{secrets.HF_TOKEN_OPTIMUM_NEURON_CACHE}} \ | |
| python tools/auto_fill_inference_cache.py --config_file ${config_prefix_url}/${{matrix.config}}.json |