a

Author: matthewkotila

.github/workflows/test.yaml

@@ -0,0 +1,37 @@
+# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+name: Test Suite
+on: push
+
+jobs:
+  unit-tests:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+        with:
+          python-version: 3.10
+          activate-environment: true
+      - name: Install dependencies
+        run: uv pip install ".[dev]"
+      - name: Run unit tests
+        run: pytest tests --ignore=tests/integration -v
+
+  integration-tests:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+        with:
+          python-version: 3.10
+          activate-environment: true
+      - name: Install dependencies
+        run: |
+          uv pip install ".[dev]"
+          uv pip install "./integration-tests[dev]"
+      - name: Run integration tests
+        run: pytest tests/integration -v

tests/integration/__init__.py

@@ -0,0 +1,2 @@
+# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0

tests/integration/basic_end_to_end.py

@@ -0,0 +1,82 @@
+# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+
+import pytest
+import requests
+import time
+import subprocess
+from pathlib import Path
+
+
+class TestAIPerfMockServerIntegration:
+    @pytest.fixture(scope="class")
+    def test_server(self):
+        """Start a test LLM inference server for integration testing"""
+        # Start test server (e.g., vLLM, Triton, etc.)
+        server_process = subprocess.Popen(
+            [
+                "aiperf-mock-server",
+                "-m",
+                "Qwen/Qwen3-0.6B",
+                "-p",
+                "8080",
+            ]
+        )
+
+        # Wait for server to be ready
+        self._wait_for_server_ready("http://127.0.0.1:8080")
+
+        yield "http://127.0.0.1:8080"
+
+        # Cleanup
+        server_process.terminate()
+        server_process.wait()
+
+    def _wait_for_server_ready(self, url, timeout=60):
+        """Wait for server to become ready"""
+        start_time = time.time()
+        while time.time() - start_time < timeout:
+            try:
+                response = requests.get(f"{url}/health", timeout=5)
+                if response.status_code == 200:
+                    return
+            except requests.exceptions.RequestException:
+                pass
+            time.sleep(2)
+        raise RuntimeError("Server failed to start within timeout")
+
+    def test_basic_performance_analysis(self, test_server):
+        """Test basic throughput and latency measurement"""
+        # Run your CLI tool against the test server
+        result = subprocess.run(
+            [
+                "aiperf",
+                "profile",
+                "--model-names",
+                "Qwen/Qwen3-0.6B",
+                "--concurrency",
+                "1",
+                "--request-count",
+                "1",
+            ],
+            capture_output=True,
+            text=True,
+        )
+
+        assert result.returncode == 0, f"aiperf failed: {result.stderr}"
+
+        # Parse and validate output
+        import json
+
+        output = json.loads(result.stdout)
+
+        # Verify key metrics are present
+        assert "ttft_avg" in output
+        assert "tpot_avg" in output
+        assert "throughput_tokens_per_sec" in output
+        assert "request_throughput" in output
+
+        # Verify metrics are reasonable
+        assert output["ttft_avg"] > 0
+        assert output["tpot_avg"] > 0
+        assert output["throughput_tokens_per_sec"] > 0