diff --git a/.github/workflows/ci-playground.yaml b/.github/workflows/ci-playground.yaml new file mode 100644 index 000000000..5de257781 --- /dev/null +++ b/.github/workflows/ci-playground.yaml @@ -0,0 +1,77 @@ +name: Build and Push playground container +run-name: Build and Push playground container +on: + workflow_dispatch: + #schedule: + # - cron: "0 10 * * *" + push: + branches: + - main + - kvant + tags: + - 'v*' + pull_request: + branches: + - main + - kvant +env: + IMAGE: git.kvant.cloud/${{github.repository}}-playground +jobs: + build_concierge_backend: + runs-on: ubuntu-latest + services: + registry: + image: registry:2 + ports: + - 5000:5000 + steps: + - name: Checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Set current time + uses: https://github.com/gerred/actions/current-time@master + id: current_time + + - name: Set up Docker Buildx + uses: docker/setup-buildx-action@v3 + + - name: Login to git.kvant.cloud registry + uses: docker/login-action@v3 + with: + registry: git.kvant.cloud + username: ${{ vars.ORG_PACKAGE_WRITER_USERNAME }} + password: ${{ secrets.ORG_PACKAGE_WRITER_TOKEN }} + + - name: Docker meta + id: meta + uses: docker/metadata-action@v5 + with: + # list of Docker images to use as base name for tags + images: | + ${{env.IMAGE}} + # generate Docker tags based on the following events/attributes + tags: | + type=schedule + type=ref,event=branch + type=ref,event=pr + type=semver,pattern={{version}} + + - name: Build and push to gitea registry + uses: docker/build-push-action@v6 + with: + push: ${{ github.event_name != 'pull_request' }} + tags: ${{ steps.meta.outputs.tags }} + labels: ${{ steps.meta.outputs.labels }} + context: llama_stack/distribution/ui + file: llama_stack/distribution/ui/Containerfile + provenance: mode=max + sbom: true + build-args: | + BUILD_DATE=${{ steps.current_time.outputs.time }} + cache-from: | + type=registry,ref=${{ env.IMAGE }}:buildcache + type=registry,ref=${{ env.IMAGE }}:${{ github.ref_name }} + type=registry,ref=${{ env.IMAGE }}:main + cache-to: type=registry,ref=${{ env.IMAGE }}:buildcache,mode=max,image-manifest=true diff --git a/llama_stack/templates/kvant/run.yaml b/llama_stack/templates/kvant/run.yaml index 4f3a00f57..9caa78567 100644 --- a/llama_stack/templates/kvant/run.yaml +++ b/llama_stack/templates/kvant/run.yaml @@ -15,7 +15,7 @@ providers: - provider_id: kvant provider_type: remote::vllm config: - url: ${env.VLLM_URL:https://maas.kvant.cloud/v1} + url: ${env.VLLM_URL:https://maas.ai-2.kvant.cloud/v1} max_tokens: ${env.VLLM_MAX_TOKENS:400000} api_token: ${env.VLLM_API_TOKEN:fake} tls_verify: ${env.VLLM_TLS_VERIFY:true}