remove benchmark and update cargo.toml file

.github/workflows/build.yaml

@@ -1,10 +1,11 @@
-name: Build and push docker image to internal registry
+name: Build and push docker image to ghcr
 
 on:
   workflow_dispatch:
   push:
     branches:
       - 'main'
+      - 'gha-setup'
     tags:
       - 'v*'
   pull_request:
@@ -14,102 +15,40 @@ on:
       - '.github/workflows/build.yaml'
 
 jobs:
-  start-runner:
-    name: Start self-hosted EC2 runner
-    runs-on: ubuntu-latest
-    env:
-      AWS_REGION: us-west-2
-      EC2_AMI_ID: ami-08e9a170e7569aa18
-      EC2_INSTANCE_TYPE: g5.12xlarge
-      EC2_SUBNET_ID: subnet-80a134dd,subnet-494de903,subnet-57f74d2f,subnet-b2343999
-      EC2_SECURITY_GROUP: sg-0a318ff79a05ddc47
-    outputs:
-      label: ${{ steps.start-ec2-runner.outputs.label }}
-      ec2-instance-id: ${{ steps.start-ec2-runner.outputs.ec2-instance-id }}
-    steps:
-      - name: Configure AWS credentials
-        uses: aws-actions/configure-aws-credentials@v1
-        with:
-          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
-          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-          aws-region: ${{ env.AWS_REGION }}
-      - name: Start EC2 runner
-        id: start-ec2-runner
-        uses: philschmid/philschmid-ec2-github-runner@main
-        with:
-          mode: start
-          github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
-          ec2-image-id: ${{ env.EC2_AMI_ID }}
-          ec2-instance-type: ${{ env.EC2_INSTANCE_TYPE }}
-          subnet-id: ${{ env.EC2_SUBNET_ID }}
-          security-group-id: ${{ env.EC2_SECURITY_GROUP }}
-          aws-resource-tags: > # optional, requires additional permissions
-            [
-              {"Key": "Name", "Value": "ec2-tgi-github-runner"},
-              {"Key": "GitHubRepository", "Value": "${{ github.repository }}"}
-            ]
-
   build-and-push-image:
     concurrency:
       group: ${{ github.workflow }}-${{ github.job }}-${{ github.head_ref || github.run_id }}
       cancel-in-progress: true
-    needs: start-runner # required to start the main job when the runner is ready
-    runs-on: ${{ needs.start-runner.outputs.label }} # run the job on the newly created runner
+    runs-on: a100-runner
     permissions:
       contents: write
       packages: write
       # This is used to complete the identity challenge
       # with sigstore/fulcio when running outside of PRs.
       id-token: write
       security-events: write
-    env:
-      AWS_REGION: us-west-2
 
     steps:
       - name: Checkout repository
         uses: actions/checkout@v3
-      - name: Initialize Docker Buildx
-        uses: docker/[email protected]
-        with:
-          install: true
-      - name: Inject slug/short variables
-        uses: rlespinasse/[email protected]
-
-      - name: Configure AWS credentials
-        uses: aws-actions/configure-aws-credentials@v1
-        with:
-          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
-          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-          aws-region: ${{ env.AWS_REGION }}
 
-      - name: Login to Amazon ECR
-        id: login-ecr
-        uses: aws-actions/[email protected]
+      - name: Set output
+        id: vars
+        run: echo "sha_short=$(git rev-parse --short HEAD)" >> $GITHUB_OUTPUT
 
-      - name: "run build script"
-        run : |
-          bash build.sh --latest
-
-  stop-runner:
-    name: Stop self-hosted EC2 runner
-    needs:
-      - start-runner
-      - build-and-push-image
-    runs-on: ubuntu-latest
-    env:
-      AWS_REGION: us-west-2
-    if: ${{ always() }} # required to stop the runner even if the error happened in the previous jobs
-    steps:
-      - name: Configure AWS credentials
-        uses: aws-actions/configure-aws-credentials@v1
+      - name: Log in to GitHub Container Registry
+        uses: docker/login-action@v1
         with:
-          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
-          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-          aws-region: ${{ env.AWS_REGION }}
-      - name: Stop EC2 runner
-        uses: philschmid/philschmid-ec2-github-runner@main
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GHCR_PAT }}
+
+      - name: Build and Push Image
+        uses: docker/build-push-action@v2
         with:
-          mode: stop
-          github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
-          label: ${{ needs.start-runner.outputs.label }}
-          ec2-instance-id: ${{ needs.start-runner.outputs.ec2-instance-id }}
+          context: .
+          file: ./Dockerfile  # Path to your Dockerfile
+          push: true
+          tags: |
+            ghcr.io/predibase/lorax:${{ steps.vars.outputs.sha_short }}
+            ghcr.io/predibase/lorax:latest

Cargo.toml

@@ -1,17 +1,16 @@
 [workspace]
 members = [
-    "benchmark",
     "router",
     "router/client",
     "router/grpc-metadata",
     "launcher"
 ]
 
 [workspace.package]
-version = "0.9.4"
+version = "0.1.0"
 edition = "2021"
-authors = ["Olivier Dehaene"]
-homepage = "https://github.com/huggingface/text-generation-inference"
+authors = ["Predibase", "Olivier Dehaene"]
+homepage = "https://github.com/predibase/lorax"
 
 [profile.release]
 debug = 1

Dockerfile

@@ -8,7 +8,6 @@ FROM chef as planner
 COPY Cargo.toml Cargo.toml
 COPY rust-toolchain.toml rust-toolchain.toml
 COPY proto proto
-COPY benchmark benchmark
 COPY router router
 COPY launcher launcher
 RUN cargo chef prepare --recipe-path recipe.json
@@ -30,7 +29,6 @@ RUN cargo chef cook --release --recipe-path recipe.json
 COPY Cargo.toml Cargo.toml
 COPY rust-toolchain.toml rust-toolchain.toml
 COPY proto proto
-COPY benchmark benchmark
 COPY router router
 COPY launcher launcher
 RUN cargo build --release
@@ -199,8 +197,6 @@ RUN cd server && \
     make gen-server && \
     pip install ".[bnb, accelerate, quantize]" --no-cache-dir
 
-# Install benchmarker
-COPY --from=builder /usr/src/target/release/text-generation-benchmark /usr/local/bin/text-generation-benchmark
 # Install router
 COPY --from=builder /usr/src/target/release/text-generation-router /usr/local/bin/text-generation-router
 # Install launcher