chore: cleanup basic e2e and test docs e2e tests, remove README skip section

Author: lkomali

tests/ci/basic_end_to_end/setup_test.sh

@@ -0,0 +1,19 @@
+#!/usr/bin/env bash
+# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+
+echo "Starting dynamo server with model ${MODEL}"
+
+bash -x ${AIPERF_SOURCE_DIR}tests/ci/${CI_JOB_NAME}/start_server.sh
+
+echo "Running aiperf functionality tests in container"
+
+docker run \
+    --rm \
+    --gpus all \
+    --network host \
+    -w /aiperf \
+    -v ${AIPERF_SOURCE_DIR}:/aiperf \
+    -e CI_JOB_NAME=${CI_JOB_NAME} \
+    -e MODEL=${MODEL} \
+    ubuntu:24.04 /bin/bash -x /aiperf/tests/ci/common/setup_aiperf.sh

tests/ci/basic_end_to_end/start_server.sh

@@ -2,17 +2,21 @@
 # SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
-# This script now uses the main.py --all-servers approach
-# instead of manually starting servers
-
 set -x
 
-echo "Starting end-to-end documentation tests using main.py --all-servers"
+time docker pull ${DYNAMO_PREBUILT_IMAGE_TAG}
+
+DYNAMO_REPO_TAG=$(docker run --rm --entrypoint "" ${DYNAMO_PREBUILT_IMAGE_TAG} cat /workspace/version.txt | cut -d'+' -f2)
+
+curl -O https://raw.githubusercontent.com/ai-dynamo/dynamo/${DYNAMO_REPO_TAG}/deploy/docker-compose.yml
 
-# Navigate to the test directory
-cd "$(dirname "$0")"
+docker compose -f docker-compose.yml down || true
 
-# Execute the main.py script with --all-servers flag
-python3 main.py --all-servers
+docker compose -f docker-compose.yml up -d
 
-echo "End-to-end documentation tests completed"
+docker run \
+  --rm \
+  --gpus all \
+  --network host \
+  ${DYNAMO_PREBUILT_IMAGE_TAG} \
+    /bin/bash -c "python3 -m dynamo.frontend & python3 -m dynamo.vllm --model ${MODEL} --enforce-eager --no-enable-prefix-caching" > ${AIPERF_SOURCE_DIR}/server.log 2>&1 &

tests/ci/basic_end_to_end/test.sh

@@ -3,8 +3,8 @@
 # SPDX-License-Identifier: Apache-2.0
 
 # TODO: switch to the commented code when dynamo 0.4.1 is released
-# timeout 5m /bin/bash -c 'while ! curl -s localhost:8080/v1/models | jq -en "input | (.data // []) | length > 0" > /dev/null 2>&1; do sleep 1; done'
-timeout 5m /bin/bash -c 'while [ "$(curl -s -o /dev/null -w "%{http_code}" localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '"'"'{"model":"Qwen/Qwen3-0.6B","messages":[{"role":"user","content":"a"}],"max_completion_tokens":1}'"'"')" != "200" ]; do sleep 1; done'
+# timeout 5m /bin/bash -c 'while ! curl -s localhost:8000/v1/models | jq -en "input | (.data // []) | length > 0" > /dev/null 2>&1; do sleep 1; done'
+timeout 5m /bin/bash -c 'while [ "$(curl -s -o /dev/null -w "%{http_code}" localhost:8000/v1/chat/completions -H "Content-Type: application/json" -d '"'"'{"model":"Qwen/Qwen3-0.6B","messages":[{"role":"user","content":"a"}],"max_completion_tokens":1}'"'"')" != "200" ]; do sleep 1; done'
 
 if [ $? -eq 124 ]; then
   echo -e "\033[0;36m╔════════════════════════════════════════╗\033[0m"
@@ -23,7 +23,7 @@ echo -e "\033[0;36m╔═══════════════════
 echo -e "\033[0;36m║           *** AIPERF LOG ***           ║\033[0m"
 echo -e "\033[0;36m╚════════════════════════════════════════╝\033[0m"
 
-timeout 5m aiperf profile --model-names ${MODEL} -u localhost:8080 --concurrency 100 --request-count 300
+timeout 5m aiperf profile --model-names ${MODEL} -u localhost:8000 --concurrency 100 --request-count 300
 
 EXIT_CODE=$?
 
@@ -49,4 +49,4 @@ elif [ ${EXIT_CODE} -ne 0 ]; then
   echo -e "\033[0;31m║    See aiperf and server logs above    ║\033[0m"
   echo -e "\033[0;31m╚════════════════════════════════════════╝\033[0m"
   exit 1
-fi
+fi

tests/ci/common/setup_test.sh tests/ci/common/setup_aiperf.shtests/ci/common/setup_test.sh renamed to tests/ci/common/setup_aiperf.sh

@@ -1,3 +1,5 @@
+# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
 """
 Constants for the end-to-end testing framework.
 """
@@ -20,5 +22,5 @@
 # Timeouts
 SETUP_MONITOR_TIMEOUT = 30  # seconds to monitor setup output
 CONTAINER_BUILD_TIMEOUT = 600  # seconds for Docker build
-CONTAINER_START_TIMEOUT = 60   # seconds for container startup
-AIPERF_COMMAND_TIMEOUT = 300   # seconds for AIPerf commands
+CONTAINER_START_TIMEOUT = 60  # seconds for container startup
+AIPERF_COMMAND_TIMEOUT = 300  # seconds for AIPerf commands

tests/ci/basic_end_to_end/constants.py …sts/ci/test_docs_end_to_end/constants.pytests/ci/basic_end_to_end/constants.py renamed to tests/ci/test_docs_end_to_end/constants.py tests/ci/basic_end_to_end/constants.py renamed to tests/ci/test_docs_end_to_end/constants.py

@@ -1,23 +1,28 @@
+# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
 """
 Data models for the end-to-end testing framework.
 """
 
 from dataclasses import dataclass
-from typing import List, Optional
+
 
 @dataclass
 class Command:
     """Represents a command extracted from markdown"""
+
     tag_name: str
     command: str
     file_path: str
     start_line: int
     end_line: int
 
+
 @dataclass
 class Server:
     """Represents a server with its setup, health check, and aiperf commands"""
+
     name: str
-    setup_command: Optional[Command]
-    health_check_command: Optional[Command]
-    aiperf_commands: List[Command]
+    setup_command: Command | None
+    health_check_command: Command | None
+    aiperf_commands: list[Command]

tests/ci/basic_end_to_end/data_types.py …ts/ci/test_docs_end_to_end/data_types.pytests/ci/basic_end_to_end/data_types.py renamed to tests/ci/test_docs_end_to_end/data_types.py tests/ci/basic_end_to_end/data_types.py renamed to tests/ci/test_docs_end_to_end/data_types.py

@@ -1,14 +1,15 @@
 #!/usr/bin/env python3
+# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
 """
 Simple end-to-end test tool for AIPerf documentation.
 
 Parses markdown files for server setup and AIPerf run commands,
 builds AIPerf container, and executes tests.
 """
 
-import sys
 import logging
-from pathlib import Path
+import sys
 
 from parser import MarkdownParser
 from test_runner import TestRunner
@@ -18,47 +19,67 @@
 setup_logging()
 logger = logging.getLogger(__name__)
 
+
 def main():
     """Main function"""
     import argparse
-    
-    parser = argparse.ArgumentParser(description="Run end-to-end tests from markdown documentation")
-    parser.add_argument("--dry-run", action="store_true", help="Show discovered commands without executing")
-    parser.add_argument("--all-servers", action="store_true", help="Run tests for all discovered servers")
+
+    parser = argparse.ArgumentParser(
+        description="Run end-to-end tests from markdown documentation"
+    )
+    parser.add_argument(
+        "--dry-run",
+        action="store_true",
+        help="Show discovered commands without executing",
+    )
+    parser.add_argument(
+        "--all-servers",
+        action="store_true",
+        help="Run tests for all discovered servers",
+    )
     args = parser.parse_args()
-    
+
     # Get repository root using centralized function
     repo_root = get_repo_root()
-    
+
     # Parse markdown files
     md_parser = MarkdownParser()
     servers = md_parser.parse_directory(str(repo_root))
-    
+
     if not servers:
         logger.warning("No servers found")
         return 0
-    
+
     logger.info(f"Discovered {len(servers)} servers:")
     for name, server in servers.items():
-        setup_file = server.setup_command.file_path if server.setup_command else "MISSING"
-        health_file = server.health_check_command.file_path if server.health_check_command else "MISSING"
+        setup_file = (
+            server.setup_command.file_path if server.setup_command else "MISSING"
+        )
+        health_file = (
+            server.health_check_command.file_path
+            if server.health_check_command
+            else "MISSING"
+        )
         aiperf_count = len(server.aiperf_commands)
-        logger.info(f"  {name}: setup={setup_file}, health={health_file}, aiperf_commands={aiperf_count}")
-    
+        logger.info(
+            f"  {name}: setup={setup_file}, health={health_file}, aiperf_commands={aiperf_count}"
+        )
+
     if args.dry_run:
         logger.info("Dry run completed")
         return 0
-    
+
     # Run tests
     runner = TestRunner()
     success = runner.run_tests(servers)
-    
+
     if success:
         logger.info("All tests passed!")
         return 0
     else:
         logger.error("Some tests failed")
         return 1
 
+
 if __name__ == "__main__":
-    sys.exit(main())
+    sys.exit(main())