diff --git a/.github/workflows/build.yaml b/.github/workflows/build.yaml index 22fa06e3..0df645ca 100644 --- a/.github/workflows/build.yaml +++ b/.github/workflows/build.yaml @@ -19,6 +19,7 @@ jobs: docker_devices: ${{ steps.final.outputs.docker_devices }} runs_on: ${{ steps.final.outputs.runs_on }} label: ${{ steps.final.outputs.label }} + extra_pytest: ${{ steps.final.outputs.extra_pytest }} concurrency: group: ${{ github.workflow }}-build-and-push-image-${{ inputs.hardware }}-${{ github.head_ref || github.run_id }} cancel-in-progress: true @@ -39,6 +40,7 @@ jobs: - name: Construct harware variables shell: bash run: | + export extra_pytest="" case ${{ inputs.hardware }} in cuda) export dockerfile="Dockerfile" @@ -50,9 +52,8 @@ jobs: export dockerfile="Dockerfile_amd" export label_extension="-rocm" export docker_devices="/dev/kfd,/dev/dri" - # TODO Re-enable when they pass. - # export runs_on="amd-gpu-tgi" - export runs_on="ubuntu-latest" + export runs_on="amd-gpu-tgi" + export extra_pytest="-k flash_llama_grammar_tools" ;; intel) export dockerfile="Dockerfile_intel" @@ -148,6 +149,7 @@ jobs: echo "docker_image=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:sha-${{ env.GITHUB_SHA_SHORT}}${{ env.LABEL }}" >> "$GITHUB_OUTPUT" echo "docker_devices=${{ env.DOCKER_DEVICES }}" >> "$GITHUB_OUTPUT" echo "runs_on=${{ env.RUNS_ON }}" >> "$GITHUB_OUTPUT" + echo "extra_pytest=${{ env.EXTRA_PYTEST }}" >> "$GITHUB_OUTPUT" echo "label=${{ env.LABEL }}" >> "$GITHUB_OUTPUT" integration_tests: concurrency: @@ -178,6 +180,7 @@ jobs: export DOCKER_VOLUME=/mnt/cache export DOCKER_IMAGE=${{ needs.build-and-push.outputs.docker_image }} export DOCKER_DEVICES=${{ needs.build-and-push.outputs.docker_devices }} + export EXTRA_PYTEST=${{ needs.build-and-push.outputs.extra_pytest }} export HUGGING_FACE_HUB_TOKEN=${{ secrets.HUGGING_FACE_HUB_TOKEN }} echo $DOCKER_IMAGE - pytest -s -vv integration-tests + pytest -s -vv integration-tests ${EXTRA_PYTEST}