Files
vLLM/.buildkite/test_areas/models_distributed.yaml
2026-10-15 20:11:17 -05:00

112 lines
4.0 KiB
YAML

group: Models - Distributed
depends_on:
- image-build
steps:
- label: ":nvidia: (L4) Qwen4 Exp SP"
key: qwen4-exp-sp-tests-4-gpus
timeout_in_minutes: 30
working_dir: "/vllm-workspace/tests"
device: l4
num_devices: 4
source_file_dependencies:
- vllm/config/parallel.py
- vllm/models/common/ops/sequence_parallel.py
- vllm/models/qwen4_exp/
- vllm/model_executor/layers/vocab_parallel_embedding.py
- vllm/model_executor/models/qwen3_next.py
- tests/models/qwen4_exp/test_ple.py
- tests/models/qwen4_exp/test_tpsp.py
commands:
- pytest -v -s models/qwen4_exp/test_tpsp.py
mirror:
amd:
label: ":amd: (MI355) Qwen4 Exp SP"
dind: false
device: mi355_4
depends_on:
- image-build-amd
source_file_dependencies:
- vllm/config/parallel.py
- vllm/models/common/ops/sequence_parallel.py
- vllm/models/qwen4_exp/
- vllm/model_executor/layers/vocab_parallel_embedding.py
- vllm/model_executor/models/qwen3_next.py
- vllm/platforms/rocm.py
- tests/models/qwen4_exp/test_ple.py
- tests/models/qwen4_exp/test_tpsp.py
- label: ":nvidia: (L4) Distributed Models Shard %N"
key: distributed-model-tests-2-gpus
timeout_in_minutes: 35
working_dir: "/vllm-workspace/tests"
device: l4
num_devices: 2
source_file_dependencies:
- vllm/model_executor/model_loader/sharded_state_loader.py
- vllm/model_executor/models/
- tests/basic_correctness/
- tests/model_executor/model_loader/test_sharded_state_loader.py
- tests/models/
commands:
- |
case "$$BUILDKITE_PARALLEL_JOB" in
0)
TARGET_TEST_SUITE=L4 pytest basic_correctness/ -v -s -m 'distributed(num_gpus=2)'
CUDA_VISIBLE_DEVICES=0,1 pytest -v -s model_executor/model_loader/test_sharded_state_loader.py -m '(not slow_test)'
;;
1)
pytest models/transformers/test_backend.py -v -s -m 'distributed(num_gpus=2)'
pytest models/language -v -s -m 'distributed(num_gpus=2)'
;;
2)
pytest models/multimodal -v -s -m 'distributed(num_gpus=2)' --ignore models/multimodal/generation/test_whisper.py
VLLM_WORKER_MULTIPROC_METHOD=spawn pytest models/multimodal/generation/test_whisper.py -v -s -m 'distributed(num_gpus=2)'
;;
*) exit 2 ;;
esac
parallelism: 3
mirror:
amd:
label: ":amd: (MI300) Distributed Models Shard %N"
dind: false
device: mi300_2
timeout_in_minutes: 80
depends_on:
- image-build-amd
source_file_dependencies:
- vllm/models/hy_v4/
- vllm/config/
- vllm/v1/worker/
- vllm/v1/attention/ops/
- vllm/v1/attention/backend.py
- tests/conftest.py
- tests/utils.py
- vllm/model_executor/model_loader/sharded_state_loader.py
- vllm/model_executor/models/
- vllm/model_executor/layers/
- vllm/v1/attention/backends/
- vllm/v1/attention/selector.py
- vllm/_aiter_ops.py
- vllm/platforms/rocm.py
- tests/basic_correctness/
- tests/model_executor/model_loader/test_sharded_state_loader.py
- tests/models/
commands:
- |
case "$$BUILDKITE_PARALLEL_JOB" in
0)
TARGET_TEST_SUITE=MI300 pytest basic_correctness/ -v -s -m 'distributed(num_gpus=2)' &&
HIP_VISIBLE_DEVICES=0,1 pytest -v -s model_executor/model_loader/test_sharded_state_loader.py -m '(not slow_test)'
;;
1)
pytest models/transformers/test_backend.py -v -s -m 'distributed(num_gpus=2)' &&
pytest models/language -v -s -m 'distributed(num_gpus=2)' &&
VLLM_ROCM_USE_AITER=1 pytest -v -s models/test_hyv4_rocm.py -m 'distributed(num_gpus=2)'
;;
2)
pytest models/multimodal -v -s -m 'distributed(num_gpus=2)' --ignore models/multimodal/generation/test_whisper.py &&
VLLM_WORKER_MULTIPROC_METHOD=spawn pytest models/multimodal/generation/test_whisper.py -v -s -m 'distributed(num_gpus=2)'
;;
*) exit 2 ;;
esac