[CI] Fix nonexistent dependency for data-parallel example test selection (#53026)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
This commit is contained in:
@@ -858,7 +858,7 @@ steps:
|
||||
- tests/distributed/test_torchrun_example.py
|
||||
- tests/distributed/test_torchrun_example_moe.py
|
||||
- examples/rl/
|
||||
- tests/examples/features/data_parallel/data_parallel_offline.py
|
||||
- examples/features/data_parallel/data_parallel_offline.py
|
||||
- vllm/platforms/rocm.py
|
||||
commands:
|
||||
- torchrun --nproc-per-node=4 distributed/test_torchrun_example.py
|
||||
|
||||
@@ -116,7 +116,7 @@ steps:
|
||||
- tests/distributed/test_torchrun_example.py
|
||||
- tests/distributed/test_torchrun_example_moe.py
|
||||
- examples/rl/
|
||||
- tests/examples/features/data_parallel/data_parallel_offline.py
|
||||
- examples/features/data_parallel/data_parallel_offline.py
|
||||
commands:
|
||||
# https://github.com/NVIDIA/nccl/issues/1838
|
||||
- export NCCL_CUMEM_HOST_ENABLE=0
|
||||
@@ -265,7 +265,7 @@ steps:
|
||||
- vllm/executor/
|
||||
- vllm/model_executor/models/
|
||||
- tests/distributed/
|
||||
- tests/examples/features/data_parallel/data_parallel_offline.py
|
||||
- examples/features/data_parallel/data_parallel_offline.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/features/data_parallel/data_parallel_offline.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/features/data_parallel/data_parallel_offline.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"
|
||||
|
||||
|
||||
Reference in New Issue
Block a user