From 8c6f694a79d7a607ef9ba1f865c610f15c3fc2a4 Mon Sep 17 00:00:00 2001 From: youkaichao Date: Thu, 22 Aug 2024 00:54:15 -0700 Subject: [PATCH] [ci] refine dependency for distributed tests (#7776) --- .buildkite/test-pipeline.yaml | 25 +++++++++++++++++-------- 1 file changed, 17 insertions(+), 8 deletions(-) diff --git a/.buildkite/test-pipeline.yaml b/.buildkite/test-pipeline.yaml index 4d1a997f6425f..460095429680a 100644 --- a/.buildkite/test-pipeline.yaml +++ b/.buildkite/test-pipeline.yaml @@ -95,7 +95,8 @@ steps: num_gpus: 4 fast_check: true source_file_dependencies: - - vllm/ + - vllm/distributed/ + - vllm/core/ - tests/distributed - tests/spec_decode/e2e/test_integration_dist_tp4 commands: @@ -284,8 +285,11 @@ steps: num_gpus: 2 num_nodes: 2 source_file_dependencies: - - vllm/ - - tests/distributed/test_same_node + - vllm/distributed/ + - vllm/engine/ + - vllm/executor/ + - vllm/model_executor/models/ + - tests/distributed/ commands: - # the following commands are for the first node, with ip 192.168.10.10 (ray environment already set up) - 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 @@ -298,8 +302,11 @@ steps: working_dir: "/vllm-workspace/tests" num_gpus: 2 source_file_dependencies: - - vllm/ - - tests/distributed + - vllm/distributed/ + - vllm/engine/ + - vllm/executor/ + - vllm/model_executor/models/ + - tests/distributed/ commands: - VLLM_TEST_SAME_HOST=1 torchrun --nproc-per-node=4 distributed/test_same_node.py - TARGET_TEST_SUITE=L4 pytest -v -s distributed/test_basic_distributed_correctness.py @@ -333,9 +340,11 @@ steps: working_dir: "/vllm-workspace/tests" num_gpus: 4 source_file_dependencies: - - vllm/ - - tests/distributed/test_pp_cudagraph.py - - tests/distributed/test_pipeline_parallel + - 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