refactor: vLLM to new Python UX (#1983)

Co-authored-by: Graham King <grahamk@nvidia.com>

examples/vllm/components/protocol.py → components/backends/vllm/src/dynamo/vllm/protocol.py

 # SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
 
 from typing import Any, List, Optional
 

examples/vllm/components/publisher.py → components/backends/vllm/src/dynamo/vllm/publisher.py

 # SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
 
 from typing import Optional
 

pyproject.toml

@@ -79,7 +79,7 @@ requires = ["hatchling"]
 build-backend = "hatchling.build"
 
 [tool.hatch.build.targets.wheel]
-packages = ["deploy/sdk/src/dynamo", "components/planner/src/dynamo", "components/frontend/src/dynamo", "components/backends/llama_cpp/src/dynamo", "components/backends/mocker/src/dynamo", "components/backends/trtllm/src/dynamo", "components/backends/sglang/src/dynamo"]
+packages = ["deploy/sdk/src/dynamo", "components/planner/src/dynamo", "components/frontend/src/dynamo", "components/backends/llama_cpp/src/dynamo", "components/backends/mocker/src/dynamo", "components/backends/trtllm/src/dynamo", "components/backends/sglang/src/dynamo", "components/backends/vllm/src/dynamo"]
 
 # This section is for including the binaries in the wheel package
 # but doesn't make them executable scripts in the venv bin directory

tests/serve/test_vllm.py

@@ -186,7 +186,7 @@ class VLLMProcess(ManagedProcess):
 vllm_configs = {
     "aggregated": VLLMConfig(
         name="aggregated",
-        directory="/workspace/examples/vllm",
+        directory="/workspace/components/backends/vllm",
         script_name="agg.sh",
         marks=[pytest.mark.gpu_1, pytest.mark.vllm],
         endpoints=["v1/chat/completions", "v1/completions"],
@@ -212,7 +212,7 @@ vllm_configs = {
     ),
     "disaggregated": VLLMConfig(
         name="disaggregated",
-        directory="/workspace/examples/vllm",
+        directory="/workspace/components/backends/vllm",
         script_name="disagg.sh",
         marks=[pytest.mark.gpu_2, pytest.mark.vllm],
         endpoints=["v1/chat/completions", "v1/completions"],