Skip to content

Fix generation using Jetstream Pytorch #6

Fix generation using Jetstream Pytorch

Fix generation using Jetstream Pytorch #6

name: Optimum TPU / Test TGI on TPU / Jetstream Pytorch
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 - Jetstream Pytorch
runs-on: optimum-tpu
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
env:
PJRT_DEVICE: TPU
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_jetstream