louis_lifu
/
vllm
mirror of https://github.com/vllm-project/vllm
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[ci] refine dependency for distributed tests (#7776)

This commit is contained in:
youkaichao 2024-08-22 00:54:15 -07:00 committed by GitHub
parent eeee1c3b1a
commit 8c6f694a79
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 17 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
.buildkite/test-pipeline.yaml
View File

@ -95,7 +95,8 @@ steps:
num_gpus: 4 num_gpus: 4
fast_check: true fast_check: true
source_file_dependencies: source_file_dependencies:
- vllm/ - vllm/distributed/
- vllm/core/
- tests/distributed - tests/distributed
- tests/spec_decode/e2e/test_integration_dist_tp4 - tests/spec_decode/e2e/test_integration_dist_tp4
commands: commands:
@ -284,8 +285,11 @@ steps:
num_gpus: 2 num_gpus: 2
num_nodes: 2 num_nodes: 2
source_file_dependencies: source_file_dependencies:
- vllm/ - vllm/distributed/
- tests/distributed/test_same_node - vllm/engine/
- vllm/executor/
- vllm/model_executor/models/
- tests/distributed/
commands: commands:
- # the following commands are for the first node, with ip 192.168.10.10 (ray environment already set up) - # 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 - 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" working_dir: "/vllm-workspace/tests"
num_gpus: 2 num_gpus: 2
source_file_dependencies: source_file_dependencies:
- vllm/ - vllm/distributed/
- tests/distributed - vllm/engine/
- vllm/executor/
- vllm/model_executor/models/
- tests/distributed/
commands: commands:
- VLLM_TEST_SAME_HOST=1 torchrun --nproc-per-node=4 distributed/test_same_node.py - 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 - TARGET_TEST_SUITE=L4 pytest -v -s distributed/test_basic_distributed_correctness.py
@ -333,9 +340,11 @@ steps:
working_dir: "/vllm-workspace/tests" working_dir: "/vllm-workspace/tests"
num_gpus: 4 num_gpus: 4
source_file_dependencies: source_file_dependencies:
- vllm/ - vllm/distributed/
- tests/distributed/test_pp_cudagraph.py - vllm/engine/
- tests/distributed/test_pipeline_parallel - vllm/executor/
- vllm/model_executor/models/
- tests/distributed/
commands: commands:
- pytest -v -s distributed/test_pp_cudagraph.py - pytest -v -s distributed/test_pp_cudagraph.py
- pytest -v -s distributed/test_pipeline_parallel.py - pytest -v -s distributed/test_pipeline_parallel.py