group: Distributed
depends_on: 
  - image-build
steps:
- label: Distributed Comm Ops
  timeout_in_minutes: 20
  working_dir: "/vllm-workspace/tests"
  num_devices: 2
  source_file_dependencies:
  - vllm/distributed
  - tests/distributed
  commands:
  - pytest -v -s distributed/test_comm_ops.py
  - pytest -v -s distributed/test_shm_broadcast.py
  - pytest -v -s distributed/test_shm_buffer.py
  - pytest -v -s distributed/test_shm_storage.py

- label: Distributed (2 GPUs)
  timeout_in_minutes: 60
  working_dir: "/vllm-workspace/tests"
  num_devices: 2
  source_file_dependencies:
  - vllm/compilation/
  - vllm/distributed/
  - vllm/engine/
  - vllm/executor/
  - vllm/worker/worker_base.py
  - vllm/v1/engine/
  - vllm/v1/worker/
  - tests/compile/fullgraph/test_basic_correctness.py
  - tests/compile/test_wrapper.py
  - tests/distributed/
  - tests/entrypoints/llm/test_collective_rpc.py
  - tests/v1/distributed
  - tests/v1/entrypoints/openai/test_multi_api_servers.py
  - tests/v1/shutdown
  - tests/v1/worker/test_worker_memory_snapshot.py
  commands:
  # https://github.com/NVIDIA/nccl/issues/1838
  - export NCCL_CUMEM_HOST_ENABLE=0
  - TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_async_llm_dp.py
  - TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_eagle_dp.py
  - TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_external_lb_dp.py
  - DP_SIZE=2 pytest -v -s v1/entrypoints/openai/test_multi_api_servers.py
  - pytest -v -s entrypoints/llm/test_collective_rpc.py
  - pytest -v -s ./compile/fullgraph/test_basic_correctness.py
  - pytest -v -s ./compile/test_wrapper.py
  - VLLM_TEST_SAME_HOST=1 torchrun --nproc-per-node=4 distributed/test_same_node.py | grep 'Same node test passed'
  - VLLM_TEST_SAME_HOST=1 VLLM_TEST_WITH_DEFAULT_DEVICE_SET=1 torchrun --nproc-per-node=4 distributed/test_same_node.py | grep 'Same node test passed'
  - CUDA_VISIBLE_DEVICES=0,1 pytest -v -s v1/shutdown
  - pytest -v -s v1/worker/test_worker_memory_snapshot.py

- label: Distributed Tests (4 GPUs)
  timeout_in_minutes: 50
  working_dir: "/vllm-workspace/tests"
  num_devices: 4
  source_file_dependencies:
  - vllm/distributed/
  - tests/distributed/test_utils
  - tests/distributed/test_pynccl
  - tests/distributed/test_events
  - tests/compile/fullgraph/test_basic_correctness.py
  - examples/offline_inference/rlhf.py
  - examples/offline_inference/rlhf_colocate.py
  - examples/offline_inference/new_weight_syncing/
  - tests/examples/offline_inference/data_parallel.py
  - tests/v1/distributed
  - tests/v1/engine/test_engine_core_client.py
  - tests/distributed/test_symm_mem_allreduce.py
  commands:
  # https://github.com/NVIDIA/nccl/issues/1838
  - export NCCL_CUMEM_HOST_ENABLE=0
  # test with torchrun tp=2 and external_dp=2
  - torchrun --nproc-per-node=4 distributed/test_torchrun_example.py
  # test with torchrun tp=2 and pp=2
  - PP_SIZE=2 torchrun --nproc-per-node=4 distributed/test_torchrun_example.py
  # test with torchrun tp=4 and dp=1
  - TP_SIZE=4 torchrun --nproc-per-node=4 distributed/test_torchrun_example_moe.py
  # test with torchrun tp=2, pp=2 and dp=1
  - PP_SIZE=2 TP_SIZE=2 torchrun --nproc-per-node=4 distributed/test_torchrun_example_moe.py
  # test with torchrun tp=1 and dp=4 with ep
  - DP_SIZE=4 ENABLE_EP=1 torchrun --nproc-per-node=4 distributed/test_torchrun_example_moe.py
  # test with torchrun tp=2 and dp=2 with ep
  - TP_SIZE=2 DP_SIZE=2 ENABLE_EP=1 torchrun --nproc-per-node=4 distributed/test_torchrun_example_moe.py
  # test with internal dp
  - python3 ../examples/offline_inference/data_parallel.py --enforce-eager
  - TP_SIZE=2 DP_SIZE=2 pytest -v -s v1/distributed/test_async_llm_dp.py
  - TP_SIZE=2 DP_SIZE=2 pytest -v -s v1/distributed/test_eagle_dp.py
  - TP_SIZE=2 DP_SIZE=2 pytest -v -s v1/distributed/test_external_lb_dp.py
  - TP_SIZE=1 DP_SIZE=4 pytest -v -s v1/distributed/test_internal_lb_dp.py
  - TP_SIZE=1 DP_SIZE=4 pytest -v -s v1/distributed/test_hybrid_lb_dp.py
  - pytest -v -s v1/engine/test_engine_core_client.py::test_kv_cache_events_dp
  - pytest -v -s distributed/test_utils.py
  - pytest -v -s compile/fullgraph/test_basic_correctness.py
  - pytest -v -s distributed/test_pynccl.py
  - pytest -v -s distributed/test_events.py
  - pytest -v -s distributed/test_symm_mem_allreduce.py
  # TODO: create a dedicated test section for multi-GPU example tests
  # when we have multiple distributed example tests
  # OLD rlhf examples
  - cd ../examples/offline_inference
  - VLLM_ALLOW_INSECURE_SERIALIZATION=1 python3 rlhf.py
  - VLLM_ALLOW_INSECURE_SERIALIZATION=1 RAY_DEDUP_LOGS=0 python3 rlhf_colocate.py
  # NEW rlhf examples
  - cd new_weight_syncing
  - VLLM_ALLOW_INSECURE_SERIALIZATION=1 python3 rlhf_nccl.py
  - VLLM_ALLOW_INSECURE_SERIALIZATION=1 python3 rlhf_ipc.py

- label: Distributed Tests (8 GPUs)(H100)
  timeout_in_minutes: 10
  device: h100
  num_devices: 8
  working_dir: "/vllm-workspace/tests"
  source_file_dependencies:
  - examples/offline_inference/torchrun_dp_example.py
  - vllm/config/parallel.py
  - vllm/distributed/
  - vllm/v1/engine/llm_engine.py
  - vllm/v1/executor/uniproc_executor.py
  - vllm/v1/worker/gpu_worker.py
  commands:
  # https://github.com/NVIDIA/nccl/issues/1838
  - export NCCL_CUMEM_HOST_ENABLE=0
  # test with torchrun tp=2 and dp=4 with ep
  - torchrun --nproc-per-node=8 ../examples/offline_inference/torchrun_dp_example.py --tp-size=2 --pp-size=1 --dp-size=4 --enable-ep

- label: Distributed Tests (4 GPUs)(A100)
  device: a100
  optional: true
  num_devices: 4
  source_file_dependencies:
  - vllm/
  commands:
  # NOTE: don't test llama model here, it seems hf implementation is buggy
  # see https://github.com/vllm-project/vllm/pull/5689 for details
  - pytest -v -s distributed/test_custom_all_reduce.py
  - torchrun --nproc_per_node=2 distributed/test_ca_buffer_sharing.py
  - TARGET_TEST_SUITE=A100 pytest basic_correctness/ -v -s -m 'distributed(num_gpus=2)'
  - pytest -v -s -x lora/test_mixtral.py

- label: Distributed Tests (2 GPUs)(H100)
  timeout_in_minutes: 15
  device: h100
  optional: true
  working_dir: "/vllm-workspace/"
  num_devices: 2
  commands:
    - pytest -v -s tests/distributed/test_context_parallel.py
    - VLLM_ALLOW_INSECURE_SERIALIZATION=1 python3 examples/offline_inference/new_weight_syncing/rlhf_async_new_apis.py
    - VLLM_USE_DEEP_GEMM=1 VLLM_LOGGING_LEVEL=DEBUG python3 examples/offline_inference/data_parallel.py --model=Qwen/Qwen1.5-MoE-A2.7B -tp=1 -dp=2 --max-model-len=2048 --all2all-backend=deepep_high_throughput
    - pytest -v -s tests/v1/distributed/test_dbo.py

- label: Distributed Tests (2 GPUs)(B200)
  device: b200
  optional: true
  working_dir: "/vllm-workspace/"
  num_devices: 2
  commands:
    - pytest -v -s tests/distributed/test_context_parallel.py
    - pytest -v -s tests/distributed/test_nccl_symm_mem_allreduce.py
    - pytest -v -s tests/v1/distributed/test_dbo.py

- label: 2 Node Test (4 GPUs)
  timeout_in_minutes: 30
  working_dir: "/vllm-workspace/tests"
  num_devices: 2
  num_nodes: 2
  no_plugin: true
  optional: true # TODO: revert once infra issue solved
  source_file_dependencies:
  - vllm/distributed/
  - vllm/engine/
  - vllm/executor/
  - vllm/model_executor/models/
  - tests/distributed/
  - tests/examples/offline_inference/data_parallel.py
  commands:
    - ./.buildkite/scripts/run-multi-node-test.sh /vllm-workspace/tests 2 2 $IMAGE_TAG "VLLM_TEST_SAME_HOST=0 torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=192.168.10.10 distributed/test_same_node.py | grep 'Same node test passed' && NUM_NODES=2 torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=192.168.10.10 distributed/test_node_count.py | grep 'Node count test passed' && python3 ../examples/offline_inference/data_parallel.py -dp=2 -tp=1 --dp-num-nodes=2 --dp-node-rank=0 --dp-master-addr=192.168.10.10 --dp-master-port=12345 --enforce-eager --trust-remote-code && VLLM_MULTI_NODE=1 pytest -v -s distributed/test_multi_node_assignment.py && VLLM_MULTI_NODE=1 pytest -v -s distributed/test_pipeline_parallel.py" "VLLM_TEST_SAME_HOST=0 torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=192.168.10.10 distributed/test_same_node.py | grep 'Same node test passed' && NUM_NODES=2 torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=192.168.10.10 distributed/test_node_count.py | grep 'Node count test passed' && python3 ../examples/offline_inference/data_parallel.py -dp=2 -tp=1 --dp-num-nodes=2 --dp-node-rank=1 --dp-master-addr=192.168.10.10 --dp-master-port=12345 --enforce-eager --trust-remote-code"

- label: Distributed NixlConnector PD accuracy (4 GPUs)
  timeout_in_minutes: 30
  working_dir: "/vllm-workspace/tests"
  num_devices: 4
  source_file_dependencies:
    - vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py
    - tests/v1/kv_connector/nixl_integration/
  commands:
    - uv pip install --system -r /vllm-workspace/requirements/kv_connectors.txt
    - bash v1/kv_connector/nixl_integration/config_sweep_accuracy_test.sh

- label: DP EP Distributed NixlConnector PD accuracy tests (4 GPUs)
  timeout_in_minutes: 30
  working_dir: "/vllm-workspace/tests"
  num_devices: 4
  source_file_dependencies:
    - vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py
    - tests/v1/kv_connector/nixl_integration/
  commands:
    - uv pip install --system -r /vllm-workspace/requirements/kv_connectors.txt
    - DP_EP=1 bash v1/kv_connector/nixl_integration/config_sweep_accuracy_test.sh

- label: CrossLayer KV layout Distributed NixlConnector PD accuracy tests (4 GPUs)
  timeout_in_minutes: 30
  working_dir: "/vllm-workspace/tests"
  num_devices: 4
  source_file_dependencies:
    - vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py
    - tests/v1/kv_connector/nixl_integration/
  commands:
    - uv pip install --system -r /vllm-workspace/requirements/kv_connectors.txt
    - CROSS_LAYERS_BLOCKS=True bash v1/kv_connector/nixl_integration/config_sweep_accuracy_test.sh

- label: Pipeline + Context Parallelism (4 GPUs)
  timeout_in_minutes: 60
  working_dir: "/vllm-workspace/tests"
  num_devices: 4
  source_file_dependencies:
  - vllm/distributed/
  - vllm/engine/
  - vllm/executor/
  - vllm/model_executor/models/
  - tests/distributed/
  commands:
  - pytest -v -s distributed/test_pp_cudagraph.py
  - pytest -v -s distributed/test_pipeline_parallel.py