Quantization Jetstream Pytorch (#111) #292
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 TPU / Test TGI on TPU | |
| on: | |
| push: | |
| branches: [ main ] | |
| paths: | |
| - "text-generation-inference/**" | |
| pull_request: | |
| branches: [ main ] | |
| paths: | |
| - "text-generation-inference/**" | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }} | |
| cancel-in-progress: true | |
| jobs: | |
| do-the-job: | |
| name: Run TGI tests | |
| runs-on: | |
| group: gcp-ct5lp-hightpu-8t | |
| container: | |
| image: us-central1-docker.pkg.dev/tpu-pytorch-releases/docker/xla:r2.4.0_3.10_tpuvm | |
| options: --shm-size "16gb" --ipc host --privileged ${{ vars.V5_LITEPOD_8_ENV}} -v /mnt/hf_cache:/mnt/hf_cache | |
| env: | |
| PJRT_DEVICE: TPU | |
| HF_HUB_CACHE: /mnt/hf_cache/cache_huggingface | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v4 | |
| - name: Build and test TGI server | |
| run: | | |
| HF_TOKEN=${{ secrets.HF_TOKEN_OPTIMUM_TPU_CI }} make tgi_test |