add sliding windows using flex attention and attn_gym packages #648
Workflow file for this run
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: Install Then Test GQA Variations | |
| on: [push, pull_request] | |
| jobs: | |
| Install-And-Test-GQA: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Check out repository code | |
| uses: actions/checkout@v4 | |
| - run: echo "${{ github.repository }} repository has been cloned to the runner." | |
| - run: echo "Currently on ${{ github.ref }} branch" | |
| - name: ls of directory | |
| run: | | |
| ls ${{ github.workspace }} | |
| - name: Install CPU Dependencies | |
| run: | | |
| python3 -m venv venv | |
| source venv/bin/activate | |
| python3 -m pip install --upgrade pip | |
| python3 -m pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu | |
| python3 -m pip install numpy transformers datasets tiktoken wandb tqdm tensorboard | |
| python3 -m pip install -r requirements_cpu.txt | |
| - name: Test all softmax variations | |
| run: | | |
| source venv/bin/activate | |
| python3 data/shakespeare_char/prepare.py | |
| cd tests | |
| source test_gqa_variations_cpu.sh | |