Merge branch 'main' into CI-CD/bach

.github/runners/Dockerfile

@@ -0,0 +1,52 @@
+FROM docker.io/pytorch/pytorch:2.3.0-cuda12.1-cudnn8-runtime
+
+RUN apt-get update \
+  && apt-get install -y --no-install-recommends \
+    build-essential \
+    cmake \
+    sudo \
+    unzip \
+    curl \
+    wget \
+    git \
+    git-lfs \
+    jq \
+  && rm -rf /var/lib/apt/lists/*
+
+RUN curl "https://awscli.amazonaws.com/awscli-exe-linux-x86_64.zip" -o "awscliv2.zip" && \
+  unzip awscliv2.zip && \
+  ./aws/install
+
+ENV HOME=/home/runner
+
+RUN mkdir -p /home/runner
+
+ARG RUNNER_VERSION=2.317.0
+
+ARG RUNNER_UID=1000
+ARG DOCKER_GID=1001
+
+RUN adduser --disabled-password --gecos "" --uid $RUNNER_UID runner \
+    && groupadd docker --gid $DOCKER_GID \
+    && usermod -aG sudo runner \
+    && usermod -aG docker runner \
+    && echo "%sudo   ALL=(ALL:ALL) NOPASSWD:ALL" > /etc/sudoers \
+    && echo "Defaults env_keep += \"DEBIAN_FRONTEND\"" >> /etc/sudoers
+
+# cd into the user directory, download and unzip the github actions runner
+RUN cd /home/runner && mkdir actions-runner && cd actions-runner \
+    && curl -O -L https://github.com/actions/runner/releases/download/v${RUNNER_VERSION}/actions-runner-linux-x64-${RUNNER_VERSION}.tar.gz \
+    && tar xzf ./actions-runner-linux-x64-${RUNNER_VERSION}.tar.gz
+
+RUN chown -R runner:runner /home/runner && /home/runner/actions-runner/bin/installdependencies.sh
+
+ADD ./start.sh /home/runner/start.sh
+
+RUN chmod +x /home/runner/start.sh
+
+# Add /usr/local/cuda-11.7/compat to LD_LIBRARY_PATH
+ENV LD_LIBRARY_PATH=/usr/local/cuda-12.1/compat${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}
+
+ENTRYPOINT ["/bin/bash", "/home/runner/start.sh"]
+
+USER runner

.github/runners/start.sh

@@ -0,0 +1,21 @@
+#!/bin/bash
+
+RUNNER_REPO=$RUNNER_REPO
+RUNNER_PAT=$RUNNER_PAT
+RUNNER_GROUP=$RUNNER_GROUP
+RUNNER_LABELS=$RUNNER_LABELS
+RUNNER_NAME=$(hostname)
+
+cd /home/runner/actions-runner
+
+./config.sh --unattended --replace --url https://github.com/${RUNNER_REPO} --pat ${RUNNER_PAT} --name ${RUNNER_NAME} --runnergroup ${RUNNER_GROUP} --labels ${RUNNER_LABELS} --work /home/runner/actions-runner/_work
+
+cleanup() {
+    echo "Removing runner..."
+    ./config.sh remove --unattended --pat ${RUNNER_PAT}
+}
+
+trap 'cleanup; exit 130' INT
+trap 'cleanup; exit 143' TERM
+
+./run.sh & wait $!

.github/workflows/test-branch.yml

@@ -0,0 +1,41 @@
+name: Test - Models
+
+on:
+  push:
+    branches:
+      - 'CI-CD/bach'
+  workflow_dispatch:
+    inputs:
+      model_id:
+        description: 'Model ID on huggingface, for example: jan-hq/Jan-Llama3-0708'
+        required: true
+        default: jan-hq/Jan-Llama3-0708
+        type: string
+      dataset_id:
+        description: 'Dataset ID on huggingface, for example: jan-hq/instruction-speech-conversation-test'
+        required: true
+        default: jan-hq/instruction-speech-conversation-test
+        type: string
+      extra_args:
+        description: 'Extra arguments for python command, for example:--mode audio --num_rows 5'
+        required: false
+        default: "--mode audio --num_rows 5"
+        type: string
+
+jobs:
+  run-test:
+    runs-on: research
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Install dependencies
+        working-directory: ./tests
+        run: |
+          python3 -m pip install --upgrade pip
+          pip3 install -r requirements.txt
+
+      - name: Run tests
+        working-directory: ./tests
+        run: |
+          python3 test_case.py --model_dir ${{ github.event.inputs.model_id || 'jan-hq/Jan-Llama3-0708' }} --data_dir ${{ github.event.inputs.dataset_id || 'jan-hq/instruction-speech-conversation-test' }} ${{ github.event.inputs.extra_args || '--mode audio --num_rows 5' }}

.github/workflows/test-models.yml

@@ -0,0 +1,37 @@
+name: Test - Models
+on:
+  workflow_dispatch:
+    inputs:
+      model_id:
+        description: 'Model ID on huggingface, for example: jan-hq/Jan-Llama3-0708'
+        required: true
+        default: jan-hq/Jan-Llama3-0708
+        type: string
+      dataset_id:
+        description: 'Dataset ID on huggingface, for example: jan-hq/instruction-speech-conversation-test'
+        required: true
+        default: jan-hq/instruction-speech-conversation-test
+        type: string
+      extra_args:
+        description: 'Extra arguments for python command, for example:--mode audio --num_rows 5'
+        required: false
+        default: "--mode audio --num_rows 5"
+        type: string
+
+jobs:
+  run-test:
+    runs-on: research
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Install dependencies
+        working-directory: ./tests
+        run: |
+          python3 -m pip install --upgrade pip
+          pip3 install -r requirements.txt
+
+      - name: Run tests
+        working-directory: ./tests
+        run: |
+          python3 test_case.py --model_dir ${{ github.event.inputs.model_id }} --data_dir ${{ github.event.inputs.dataset_id }}  ${{ github.event.inputs.extra_args }}