Merge pull request #3 from RWKV/main-dev-infctx

WIP - github action setup

.github/workflows/docker-build.yml

@@ -0,0 +1,74 @@
+name: Docker Image Publish
+
+on:
+  push:
+    branches: [ "main", "main-*" ]
+    # Publish semver tags as releases.
+    tags: [ 'v*.*.*' ]
+  pull_request:
+    branches: [ "main", "main-*" ]
+
+env:
+  # Use docker.io for Docker Hub if empty
+  REGISTRY: ghcr.io
+  # github.repository as <account>/<repo>
+  IMAGE_NAME: ${{ github.repository }}
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+      # This is used to complete the identity challenge
+      # with sigstore/fulcio when running outside of PRs.
+      id-token: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+
+      # Install the cosign tool except on PR
+      # https://github.com/sigstore/cosign-installer
+      - name: Install cosign
+        if: github.event_name != 'pull_request'
+        uses: sigstore/cosign-installer@f3c664df7af409cb4873aa5068053ba9d61a57b6 #v2.6.0
+        with:
+          cosign-release: 'v1.11.0'
+
+      # Workaround: https://github.com/docker/build-push-action/issues/461
+      - name: Setup Docker buildx
+        uses: docker/setup-buildx-action@v2
+
+      # Login against a Docker registry except on PR
+      # https://github.com/docker/login-action
+      - name: Log into registry ${{ env.REGISTRY }}
+        if: github.event_name != 'pull_request'
+        uses: docker/login-action@28218f9b04b4f3f62068d7b6ce6ca5b26e35336c
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      # Extract metadata (tags, labels) for Docker
+      # https://github.com/docker/metadata-action
+      - name: Extract Docker metadata
+        id: meta
+        uses: docker/metadata-action@98669ae865ea3cffbcbaa878cf57c20bbf1c6c38
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+
+      # Build and push Docker image with Buildx (don't push on PR)
+      # https://github.com/docker/build-push-action
+      - name: Build and push Docker image
+        id: build-and-push
+        uses: docker/build-push-action@v4
+        with:
+          context: "{{defaultContext}}:docker/env-cuda-11-8"
+          push: ${{ github.event_name != 'pull_request' }} # Don't push on PR
+          tags: ["env-cuda-11-8"]
+          # tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: type=gha,src=docker/env-cuda-11-8
+          cache-to: type=gha,mode=max

.gitignore

@@ -165,6 +165,9 @@ notebook/scratch/*
 */lightning_logs/
 */config.yaml
 
+# Add .github items
+!.github/
+
 # Add back requirements.txt
 !requirements.txt
 !requirements-*.txt

docker/env-cuda-11-8/Dockerfile

@@ -0,0 +1,21 @@
+# We start from the CUDA base image
+FROM nvidia/cuda:11.8.0-cudnn8-devel-ubuntu22.04
+
+# Install ninja, and several common stuff
+RUN apt-get update && apt-get install -y ninja-build htop wget curl git
+
+# Install python3 and pip3
+RUN apt-get update && apt-get install -y python3.11 python3-pip
+
+# Install pytorch
+RUN pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
+
+# Install all the various other required packages
+RUN pip3 install lightning==2.0.5 deepspeed==0.10.0 \
+    datasets transformers \
+    ninja numexpr jsonargparse 'jsonargparse[signatures]' \
+    lm-dataformat ftfy sentencepiece tokenizers wandb
+
+# Install the misc packages we might need for the various experiments
+RUN pip3 install \
+    papermill aiocsv aiofiles