Merge branch 'main' of gitea.corredorconect.com:software-engineering/spark-vllm-docker

.gitea/workflows/build.yml

@@ -0,0 +1,53 @@
+name: Build and Push spark-vllm
+
+on:
+  push:
+    branches:
+      - main
+  workflow_dispatch:
+
+env:
+  IMAGE_NAME: spark-vllm
+  IMAGE_TAG: latest
+
+jobs:
+  docker:
+    runs-on: nix
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Log in to Gitea Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ github.server_url }}
+          username: ${{ secrets.CI_USER }}
+          password: ${{ secrets.CI_PASSWORD }}
+
+      - name: Make build script executable
+        run: chmod +x build-and-copy.sh
+
+      - name: Build image using upstream script
+        run: |
+          ./build-and-copy.sh -t ${IMAGE_NAME}:${IMAGE_TAG}
+
+      - name: Tag image
+        run: |
+          docker tag \
+            ${IMAGE_NAME}:${IMAGE_TAG} \
+            ${{ secrets.REGISTRY_HOST }}/${IMAGE_NAME}:${IMAGE_TAG}
+
+          docker tag \
+            ${IMAGE_NAME}:${IMAGE_TAG} \
+            ${{ secrets.REGISTRY_HOST }}/${IMAGE_NAME}:${GITEA_SHA::7}
+
+      - name: Push latest
+        run: |
+          docker push \
+            ${{ secrets.REGISTRY_HOST }}/${IMAGE_NAME}:${IMAGE_TAG}
+
+      - name: Push commit SHA
+        run: |
+          docker push \
+            ${{ secrets.REGISTRY_HOST }}/${IMAGE_NAME}:${GITEA_SHA::7}

README.md

@@ -1,4 +1,3 @@
-
 # vLLM Docker Optimized for DGX Spark (single or multi-node)
 
 This repository contains the Docker configuration and startup scripts to run a multi-node vLLM inference cluster using Ray. It supports InfiniBand/RDMA (NCCL) and custom environment configuration for high-performance setups.
@@ -1104,6 +1103,7 @@ The script attempts to automatically detect:
 *   **Cluster peers:** Discovered by scanning the `ETH_IF` subnet for hosts with SSH access **and** a GB10 GPU (`nvidia-smi --query-gpu=name` must return `NVIDIA GB10`).
 *   **Copy hosts (`COPY_HOSTS`):** In standard mode, same as cluster peers. In mesh mode, scanned separately on `enp1s0f0np0` and `enp1s0f1np1` subnets so that image/model transfers use the direct InfiniBand path.
 
+
 ### Manual Overrides
 
 You can override the auto-detected values if needed: