[CI] Add current PR test workflow to Buildkite/Modal (#512)

2025-06-17 13:29:22 -07:00
parent d71a4ebffc
commit 72de11abcc
5 changed files with 260 additions and 6 deletions
@@ -0,0 +1,66 @@
+env:
+  IMAGE_VERSION: "py3.12-latest"
+
+steps:
+  - block: "Start Build"
+    blocked_state: "running"
+    prompt: "Approve build?"
+
+  - label: "Trigger Tests"
+    command: |
+      echo "Current working directory: $(pwd)"
+      echo "Current branch:"
+      git branch --show-current
+      echo "Full diff:"
+      git diff --name-only $BUILDKITE_PULL_REQUEST_BASE_BRANCH...HEAD
+    plugins:
+      - monorepo-diff#v1.4.0:
+          diff: "git diff --name-only $BUILDKITE_PULL_REQUEST_BASE_BRANCH...HEAD"
+          watch:
+            - path: 
+                - "fastvideo/v1/models/encoders/**"
+                - "fastvideo/v1/models/loaders/**"
+                - "fastvideo/v1/tests/encoders/**"
+              config:
+                command: "timeout 30m .buildkite/scripts/pr_test.sh"
+                label: "Encoder Tests"
+                env:
+                  - BUILDKITE_CLEAN_CHECKOUT=true
+                  - TEST_TYPE=encoder
+                agents:
+                  queue: "default"
+            - path:
+                - "fastvideo/v1/models/vaes/**"
+                - "fastvideo/v1/models/loaders/**"
+                - "fastvideo/v1/tests/vaes/**"
+              config:
+                command: "timeout 30m .buildkite/scripts/pr_test.sh"
+                label: "VAE Tests"
+                env:
+                  - BUILDKITE_CLEAN_CHECKOUT=true
+                  - TEST_TYPE=vae
+                agents:
+                  queue: "default"
+            - path:
+                - "fastvideo/v1/models/dits/**"
+                - "fastvideo/v1/models/loaders/**"
+                - "fastvideo/v1/tests/transformers/**"
+                - "fastvideo/v1/layers/**"
+                - "fastvideo/v1/attention/**"
+              config:
+                command: "timeout 30m .buildkite/scripts/pr_test.sh"
+                label: "Transformer Tests"
+                env:
+                  - BUILDKITE_CLEAN_CHECKOUT=true
+                  - TEST_TYPE=transformer
+                agents:
+                  queue: "default"
+            - path: "fastvideo/v1/**/*.py"
+              config:
+                command: "timeout 60m .buildkite/scripts/pr_test.sh"
+                label: "SSIM Tests"
+                env:
+                  - BUILDKITE_CLEAN_CHECKOUT=true
+                  - TEST_TYPE=ssim
+                agents:
+                  queue: "default"
@@ -0,0 +1,91 @@
+#!/bin/bash
+set -uo pipefail
+
+log() {
+  echo "[$(date '+%Y-%m-%d %H:%M:%S')] $1"
+}
+
+log "=== Starting Modal test execution ==="
+
+# Change to the project directory
+cd "$(dirname "$0")/../.."
+PROJECT_ROOT=$(pwd)
+log "Project root: $PROJECT_ROOT"
+
+# Install Modal if not available
+if ! python3 -m modal --version &> /dev/null; then
+    log "Modal not found, installing..."
+    python3 -m pip install modal
+    
+    # Verify installation
+    if ! python3 -m modal --version &> /dev/null; then
+        log "Error: Failed to install modal. Please install it manually."
+        exit 1
+    fi
+fi
+
+log "modal version: $(python3 -m modal --version)"
+
+# Set up Modal authentication using Buildkite secrets
+log "Setting up Modal authentication from Buildkite secrets..."
+MODAL_TOKEN_ID=$(buildkite-agent secret get modal_token_id)
+MODAL_TOKEN_SECRET=$(buildkite-agent secret get modal_token_secret)
+
+if [ -n "$MODAL_TOKEN_ID" ] && [ -n "$MODAL_TOKEN_SECRET" ]; then
+    log "Retrieved Modal credentials from Buildkite secrets"
+    python3 -m modal token set --token-id "$MODAL_TOKEN_ID" --token-secret "$MODAL_TOKEN_SECRET" --profile buildkite-ci --activate --verify
+    if [ $? -eq 0 ]; then
+        log "Modal authentication successful"
+    else
+        log "Error: Failed to set Modal credentials"
+        exit 1
+    fi
+else
+    log "Error: Could not retrieve Modal credentials from Buildkite secrets."
+    log "Please ensure 'modal_token_id' and 'modal_token_secret' secrets are set in Buildkite."
+    exit 1
+fi
+
+MODAL_TEST_FILE="fastvideo/v1/tests/modal/pr_test.py"
+
+if [ -z "${TEST_TYPE:-}" ]; then
+    log "Error: TEST_TYPE environment variable is not set"
+    exit 1
+fi
+log "Test type: $TEST_TYPE"
+
+case "$TEST_TYPE" in
+    "encoder")
+        log "Running encoder tests..."
+        MODAL_COMMAND="python3 -m modal run $MODAL_TEST_FILE::run_encoder_tests"
+        ;;
+    "vae")
+        log "Running VAE tests..."
+        MODAL_COMMAND="python3 -m modal run $MODAL_TEST_FILE::run_vae_tests"
+        ;;
+    "transformer")
+        log "Running transformer tests..."
+        MODAL_COMMAND="python3 -m modal run $MODAL_TEST_FILE::run_transformer_tests"
+        ;;
+    "ssim")
+        log "Running SSIM tests..."
+        MODAL_COMMAND="python3 -m modal run $MODAL_TEST_FILE::run_ssim_tests"
+        ;;
+    *)
+        log "Error: Unknown test type: $TEST_TYPE"
+        exit 1
+        ;;
+esac
+
+log "Executing: $MODAL_COMMAND"
+eval "$MODAL_COMMAND"
+TEST_EXIT_CODE=$?
+
+if [ $TEST_EXIT_CODE -eq 0 ]; then
+    log "Modal test completed successfully"
+else
+    log "Error: Modal test failed with exit code: $TEST_EXIT_CODE"
+fi
+
+log "=== Test execution completed with exit code: $TEST_EXIT_CODE ==="
+exit $TEST_EXIT_CODE
@@ -160,8 +160,7 @@ def execute_command(pod_id):
    setup_steps = [
        "tar -xzf /tmp/repo.tar.gz --no-same-owner -C /workspace/",
        f"cd /workspace/{repo_name}",
-        "source /opt/conda/etc/profile.d/conda.sh",
-        "conda activate fastvideo-dev",
+        "source $HOME/.local/bin/env && source /opt/venv/bin/activate",
        args.test_command
    ]
    
@@ -105,7 +105,7 @@ jobs:
      gpu_count: 1
      volume_size: 100
      image: "ghcr.io/${{ github.repository }}/${{ github.event.inputs.custom_image || 'fastvideo-dev:latest' }}"
-      test_command: "pip install -e .[test] && pytest ./fastvideo/v1/tests/encoders -s"
+      test_command: "uv pip install -e .[test] && pytest ./fastvideo/v1/tests/encoders -s"
      timeout_minutes: 30
    secrets:
      RUNPOD_API_KEY: ${{ secrets.RUNPOD_API_KEY }}
@@ -123,7 +123,7 @@ jobs:
      gpu_count: 1
      volume_size: 100
      image: "ghcr.io/${{ github.repository }}/${{ github.event.inputs.custom_image || 'fastvideo-dev:latest' }}"
-      test_command: "pip install -e .[test] && pytest ./fastvideo/v1/tests/vaes -s"
+      test_command: "uv pip install -e .[test] && pytest ./fastvideo/v1/tests/vaes -s"
      timeout_minutes: 30
    secrets:
      RUNPOD_API_KEY: ${{ secrets.RUNPOD_API_KEY }}
@@ -141,7 +141,7 @@ jobs:
      gpu_count: 1
      volume_size: 100
      image: "ghcr.io/${{ github.repository }}/${{ github.event.inputs.custom_image || 'fastvideo-dev:latest' }}"
-      test_command: "pip install -e .[test] && pytest ./fastvideo/v1/tests/transformers -s"
+      test_command: "uv pip install -e .[test] && pytest ./fastvideo/v1/tests/transformers -s"
      timeout_minutes: 30
    secrets:
      RUNPOD_API_KEY: ${{ secrets.RUNPOD_API_KEY }}
@@ -168,7 +168,7 @@ jobs:
      volume_size: 200
      disk_size: 200
      image: "ghcr.io/${{ github.repository }}/fastvideo-dev:${{ matrix.python-version.tag }}"
-      test_command: "pip install -e .[test] && pytest ./fastvideo/v1/tests/ssim -vs"
+      test_command: "uv pip install -e .[test] && pytest ./fastvideo/v1/tests/ssim -vs"
      timeout_minutes: 60
    secrets:
      RUNPOD_API_KEY: ${{ secrets.RUNPOD_API_KEY }}
@@ -0,0 +1,98 @@
+import modal
+
+app = modal.App()
+
+import os
+
+image_version = os.getenv("IMAGE_VERSION", "latest")
+image_tag = f"ghcr.io/hao-ai-lab/fastvideo/fastvideo-dev:{image_version}"
+print(f"Using image: {image_tag}")
+
+image = (
+    modal.Image.from_registry(image_tag, add_python="3.12")
+    .apt_install("cmake", "pkg-config", "build-essential", "curl", "libssl-dev")
+    .run_commands("curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain stable")
+    .run_commands("echo 'source ~/.cargo/env' >> ~/.bashrc")
+    .env({"PATH": "/root/.cargo/bin:$PATH"})
+    .run_commands("/bin/bash -c 'source $HOME/.local/bin/env && source /opt/venv/bin/activate && cd /FastVideo && uv pip install -e .[test]'")
+)
+
+@app.function(gpu="L40S:1", image=image, timeout=1800)
+def run_encoder_tests():
+    """Run encoder tests on L40S GPU"""
+    import subprocess
+    import sys
+    import os
+    
+    os.chdir("/FastVideo")
+    
+    command = """
+    source /opt/venv/bin/activate && 
+    pytest ./fastvideo/v1/tests/encoders -s
+    """
+    
+    result = subprocess.run([
+        "/bin/bash", "-c", command
+    ], stdout=sys.stdout, stderr=sys.stderr, check=False)
+    
+    sys.exit(result.returncode)
+
+@app.function(gpu="L40S:1", image=image, timeout=1800)
+def run_vae_tests():
+    """Run VAE tests on L40S GPU"""
+    import subprocess
+    import sys
+    import os
+    
+    os.chdir("/FastVideo")
+    
+    command = """
+    source /opt/venv/bin/activate && 
+    pytest ./fastvideo/v1/tests/vaes -s
+    """
+    
+    result = subprocess.run([
+        "/bin/bash", "-c", command
+    ], stdout=sys.stdout, stderr=sys.stderr, check=False)
+    
+    sys.exit(result.returncode)
+
+@app.function(gpu="L40S:1", image=image, timeout=1800)
+def run_transformer_tests():
+    """Run transformer tests on L40S GPU"""
+    import subprocess
+    import sys
+    import os
+    
+    os.chdir("/FastVideo")
+    
+    command = """
+    source /opt/venv/bin/activate && 
+    pytest ./fastvideo/v1/tests/transformers -s
+    """
+    
+    result = subprocess.run([
+        "/bin/bash", "-c", command
+    ], stdout=sys.stdout, stderr=sys.stderr, check=False)
+    
+    sys.exit(result.returncode)
+
+@app.function(gpu="L40S:2", image=image, timeout=3600)
+def run_ssim_tests():
+    """Run SSIM tests on 2x L40S GPUs"""
+    import subprocess
+    import sys
+    import os
+    
+    os.chdir("/FastVideo")
+    
+    command = """
+    source /opt/venv/bin/activate && 
+    pytest ./fastvideo/v1/tests/ssim -vs
+    """
+    
+    result = subprocess.run([
+        "/bin/bash", "-c", command
+    ], stdout=sys.stdout, stderr=sys.stderr, check=False)
+    
+    sys.exit(result.returncode)