feat(vllm): add vLLM integration

.github/CODEOWNERS

@@ -155,6 +155,7 @@ ddtrace/contrib/internal/litellm                              @DataDog/ml-observ
 ddtrace/contrib/internal/pydantic_ai                          @DataDog/ml-observability
 ddtrace/contrib/internal/ray                                  @DataDog/ml-observability
 ddtrace/contrib/internal/mcp                                  @DataDog/ml-observability
+ddtrace/contrib/internal/vllm                                 @DataDog/ml-observability
 tests/llmobs                                                  @DataDog/ml-observability
 tests/contrib/openai                                          @DataDog/ml-observability
 tests/contrib/langchain                                       @DataDog/ml-observability
@@ -176,6 +177,7 @@ tests/contrib/litellm                                         @DataDog/ml-observ
 tests/contrib/pydantic_ai                                     @DataDog/ml-observability
 tests/contrib/ray                                             @DataDog/ml-observability
 tests/contrib/mcp                                             @DataDog/ml-observability
+tests/contrib/vllm                                            @DataDog/ml-observability
 .gitlab/tests/llmobs.yml                                      @DataDog/ml-observability
 # MLObs snapshot tests
 tests/snapshots/tests.contrib.anthropic.*                     @DataDog/ml-observability
@@ -190,6 +192,7 @@ tests/snapshots/tests.contrib.langgraph.*                     @DataDog/ml-observ
 tests/snapshots/tests.contrib.crewai.*                        @DataDog/ml-observability
 tests/snapshots/tests.contrib.openai_agents.*                 @DataDog/ml-observability
 tests/snapshots/tests.contrib.litellm.*                       @DataDog/ml-observability
+tests/snapshots/tests.contrib.vllm.*                          @DataDog/ml-observability
 
 # Remote Config
 ddtrace/internal/remoteconfig       @DataDog/remote-config @DataDog/apm-core-python

.gitlab/testrunner.yml

@@ -1,5 +1,6 @@
 variables:
   TESTRUNNER_IMAGE: registry.ddbuild.io/dd-trace-py:v73166438-4077fc2-testrunner-2025.08.08@sha256:456e32d2fdc19569fb34d705d1ccf193c179cc5364d1f93e60f825d189647c3d
+  TESTRUNNER_GPU_IMAGE: ${TESTRUNNER_IMAGE}
 
 .testrunner:
   image:
@@ -18,3 +19,23 @@ variables:
   artifacts:
     reports:
       junit: test-results/junit*.xml
+
+.testrunner_gpu:
+  image:
+    name: ${TESTRUNNER_GPU_IMAGE}
+    docker:
+      user: bits
+  # Use GPU-enabled runners
+  tags: [ "gpu:a10-amd64" ]
+  timeout: 40m
+  before_script:
+    - ulimit -c unlimited
+    - git config --global --add safe.directory ${CI_PROJECT_DIR}
+    - pyenv global 3.12 3.8 3.9 3.10 3.11 3.13
+    - export _CI_DD_AGENT_URL=http://${HOST_IP}:8126/
+    - export NVIDIA_VISIBLE_DEVICES=all
+    - export NVIDIA_DRIVER_CAPABILITIES=compute,utility
+  retry: 2
+  artifacts:
+    reports:
+      junit: test-results/junit*.xml

.gitlab/tests.yml

@@ -43,7 +43,6 @@ include:
     DD_FAST_BUILD = "1"
 
 
-
 .test_base_hatch_snapshot:
   extends: .test_base_hatch
   services:
@@ -54,6 +53,49 @@ include:
     # agent at that host. Therefore setting this as a variable will cause recursive requests to the testagent
     - export DD_TRACE_AGENT_URL="http://testagent:9126"
 
+# GPU variants of base templates
+.test_base_hatch_gpu:
+  extends: .testrunner_gpu
+  stage: hatch
+  needs: [ prechecks ]
+  parallel: 2
+  variables:
+    # Request==Limit to achieve Guaranteed QoS; requires Kubernetes executor support
+    KUBERNETES_MEMORY_REQUEST: "12Gi"
+    KUBERNETES_MEMORY_LIMIT: "12Gi"
+    KUBERNETES_CPU_REQUEST: "2"
+    KUBERNETES_CPU_LIMIT: "2"
+  before_script:
+    - !reference [.testrunner_gpu, before_script]
+  script:
+    - export PYTEST_ADDOPTS="${PYTEST_ADDOPTS} --ddtrace"
+    - export _DD_CIVISIBILITY_USE_CI_CONTEXT_PROVIDER=true
+    - export DD_FAST_BUILD="1"
+    - |
+      envs=( $(hatch env show --json | jq -r --arg suite_name "$SUITE_NAME" 'keys[] | select(. | contains($suite_name))' | sort | ./.gitlab/ci-split-input.sh) )
+      if [[ ${#envs[@]} -eq 0 ]]; then
+        echo "No hatch envs found for ${SUITE_NAME}"
+        exit 1
+      fi
+      for env in "${envs[@]}"
+      do
+        echo "Running hatch env (GPU): ${env}:test"
+        hatch run ${env}:test
+      done
+  variables:
+    CMAKE_BUILD_PARALLEL_LEVEL = "12"
+    CARGO_BUILD_JOBS = "12"
+    DD_FAST_BUILD = "1"
+    PIP_EXTRA_INDEX_URL = "https://download.pytorch.org/whl/cu124"
+
+.test_base_hatch_gpu_snapshot:
+  extends: .test_base_hatch_gpu
+  services:
+    - !reference [.services, testagent]
+  before_script:
+    - !reference [.test_base_hatch_gpu, before_script]
+    - export DD_TRACE_AGENT_URL="http://testagent:9126"
+
 # Do not define a `needs:` in order to depend on the whole `precheck` stage
 .test_base_riot:
   extends: .testrunner
@@ -101,4 +143,51 @@ include:
     - export DD_TRACE_AGENT_URL="http://testagent:9126"
     - ln -s "${CI_PROJECT_DIR}" "/home/bits/project"
 
+.test_base_riot_gpu:
+  extends: .testrunner_gpu
+  stage: riot
+  needs: [ build_base_venvs, prechecks ]
+  parallel: 2
+  variables:
+    KUBERNETES_MEMORY_REQUEST: "12Gi"
+    KUBERNETES_MEMORY_LIMIT: "12Gi"
+    KUBERNETES_CPU_REQUEST: "2"
+    KUBERNETES_CPU_LIMIT: "2"
+  services:
+    - !reference [.services, ddagent]
+  before_script:
+    - !reference [.testrunner_gpu, before_script]
+    - unset DD_SERVICE
+    - unset DD_ENV
+    - unset DD_TAGS
+    - unset DD_TRACE_REMOVE_INTEGRATION_SERVICE_NAMES_ENABLED
+  script:
+    - |
+      hashes=( $(.gitlab/scripts/get-riot-hashes.sh "${SUITE_NAME}") )
+      if [[ ${#hashes[@]} -eq 0 ]]; then
+        echo "No riot hashes found for ${SUITE_NAME}"
+        exit 1
+      fi
+      for hash in "${hashes[@]}"
+      do
+        echo "Running riot hash (GPU): ${hash}"
+        riot list "${hash}"
+        export _CI_DD_TAGS="test.configuration.riot_hash:${hash}"
+        ${RIOT_RUN_CMD} "${hash}" -- --ddtrace
+      done
+      ./scripts/check-diff ".riot/requirements/" \
+        "Changes detected after running riot. Consider deleting changed files, running scripts/compile-and-prune-test-requirements and committing the result."
+      ./scripts/check-diff "ddtrace/contrib/integration_registry/registry.yaml" \
+        "Registry YAML file (ddtrace/contrib/integration_registry/registry.yaml) was modified. Please run: scripts/integration_registry/update_and_format_registry.py and commit the changes."
+
+.test_base_riot_gpu_snapshot:
+  extends: .test_base_riot_gpu
+  services:
+    - !reference [.test_base_riot_gpu, services]
+    - !reference [.services, testagent]
+  before_script:
+    - !reference [.test_base_riot_gpu, before_script]
+    - export DD_TRACE_AGENT_URL="http://testagent:9126"
+    - ln -s "${CI_PROJECT_DIR}" "/home/bits/project"
+
 # Required jobs will appear here

.riot/requirements/2043c14.txt

@@ -0,0 +1,163 @@
+#
+# This file is autogenerated by pip-compile with Python 3.10
+# by the following command:
+#
+#    pip-compile --allow-unsafe --cert=None --client-cert=None --index-url=None --no-annotate --pip-args=None .riot/requirements/2043c14.in
+#
+aiohappyeyeballs==2.6.1
+aiohttp==3.12.15
+aiosignal==1.4.0
+annotated-types==0.7.0
+anyio==4.11.0
+astor==0.8.1
+async-timeout==5.0.1
+attrs==25.3.0
+blake3==1.0.7
+cachetools==6.2.0
+cbor2==5.7.0
+certifi==2025.8.3
+cffi==2.0.0
+charset-normalizer==3.4.3
+click==8.3.0
+cloudpickle==3.1.1
+compressed-tensors==0.11.0
+coverage[toml]==7.10.7
+cupy-cuda12x==13.6.0
+depyf==0.19.0
+dill==0.4.0
+diskcache==5.6.3
+distro==1.9.0
+dnspython==2.8.0
+einops==0.8.1
+email-validator==2.3.0
+exceptiongroup==1.3.0
+fastapi[standard]==0.118.0
+fastapi-cli[standard]==0.0.13
+fastapi-cloud-cli==0.2.1
+fastrlock==0.8.3
+filelock==3.19.1
+frozendict==2.4.6
+frozenlist==1.7.0
+fsspec==2025.9.0
+gguf==0.17.1
+h11==0.16.0
+hf-xet==1.1.10
+httpcore==1.0.9
+httptools==0.6.4
+httpx==0.28.1
+huggingface-hub==0.35.3
+hypothesis==6.45.0
+idna==3.10
+iniconfig==2.1.0
+interegular==0.3.3
+jinja2==3.1.6
+jiter==0.11.0
+jsonschema==4.25.1
+jsonschema-specifications==2025.9.1
+lark==1.2.2
+llguidance==0.7.30
+llvmlite==0.44.0
+lm-format-enforcer==0.11.3
+markdown-it-py==4.0.0
+markupsafe==3.0.3
+mdurl==0.1.2
+mistral-common[audio,image,opencv,soundfile,soxr]==1.8.5
+mock==5.2.0
+mpmath==1.3.0
+msgpack==1.1.1
+msgspec==0.19.0
+multidict==6.6.4
+networkx==3.4.2
+ninja==1.13.0
+numba==0.61.2
+numpy==2.2.6
+nvidia-cublas-cu12==12.8.4.1
+nvidia-cuda-cupti-cu12==12.8.90
+nvidia-cuda-nvrtc-cu12==12.8.93
+nvidia-cuda-runtime-cu12==12.8.90
+nvidia-cudnn-cu12==9.10.2.21
+nvidia-cufft-cu12==11.3.3.83
+nvidia-cufile-cu12==1.13.1.3
+nvidia-curand-cu12==10.3.9.90
+nvidia-cusolver-cu12==11.7.3.90
+nvidia-cusparse-cu12==12.5.8.93
+nvidia-cusparselt-cu12==0.7.1
+nvidia-nccl-cu12==2.27.3
+nvidia-nvjitlink-cu12==12.8.93
+nvidia-nvtx-cu12==12.8.90
+openai==2.0.0
+openai-harmony==0.0.4
+opencv-python-headless==4.12.0.88
+opentracing==2.4.0
+outlines-core==0.2.11
+packaging==25.0
+partial-json-parser==0.2.1.1.post6
+pillow==11.3.0
+pluggy==1.6.0
+prometheus-client==0.23.1
+prometheus-fastapi-instrumentator==7.1.0
+propcache==0.3.2
+protobuf==6.32.1
+psutil==7.1.0
+py-cpuinfo==9.0.0
+pybase64==1.4.2
+pycountry==24.6.1
+pycparser==2.23
+pydantic[email]==2.11.9
+pydantic-core==2.33.2
+pydantic-extra-types[pycountry]==2.10.5
+pygments==2.19.2
+pytest==8.4.2
+pytest-asyncio==0.21.1
+pytest-cov==7.0.0
+pytest-mock==3.15.1
+pytest-randomly==4.0.1
+python-dotenv==1.1.1
+python-json-logger==3.3.0
+python-multipart==0.0.20
+pyyaml==6.0.3
+pyzmq==27.1.0
+ray[cgraph]==2.49.2
+referencing==0.36.2
+regex==2025.9.18
+requests==2.32.5
+rich==14.1.0
+rich-toolkit==0.15.1
+rignore==0.6.4
+rpds-py==0.27.1
+safetensors==0.6.2
+scipy==1.15.3
+sentencepiece==0.2.1
+sentry-sdk==2.39.0
+setproctitle==1.3.7
+shellingham==1.5.4
+sniffio==1.3.1
+sortedcontainers==2.4.0
+soundfile==0.13.1
+soxr==1.0.0
+starlette==0.48.0
+sympy==1.14.0
+tiktoken==0.11.0
+tokenizers==0.22.1
+tomli==2.2.1
+torch==2.8.0
+torchaudio==2.8.0
+torchvision==0.23.0
+tqdm==4.67.1
+transformers==4.56.2
+triton==3.4.0
+typer==0.19.2
+typing-extensions==4.15.0
+typing-inspection==0.4.2
+urllib3==2.5.0
+uvicorn[standard]==0.37.0
+uvloop==0.21.0
+vllm==0.10.2
+watchfiles==1.1.0
+websockets==15.0.1
+xformers==0.0.32.post1
+xgrammar==0.1.23
+yarl==1.20.1
+
+# The following packages are considered to be unsafe in a requirements file:
+setuptools==80.9.0