[CI] Move Distributed Tests from H200 -> H100 (#32555)

This commit is contained in:
Robert Shaw
2026-01-18 13:25:23 -05:00
committed by GitHub
parent 327a02d8db
commit afc3622602

View File

@@ -1400,18 +1400,19 @@ steps:
- pytest -v -s tests/distributed/test_sequence_parallel.py
- pytest -v -s tests/compile/distributed/test_sequence_parallelism.py
##### H200 test #####
- label: Distributed Tests (H200) # optional
gpu: h200
- label: Distributed Tests (H100) # optional
gpu: h100
optional: true
working_dir: "/vllm-workspace/"
num_gpus: 2
commands:
- VLLM_TEST_CLEAN_GPU_MEMORY=1 pytest -v -s tests/compile/distributed/test_async_tp.py
- pytest -v -s tests/distributed/test_context_parallel.py
- CUDA_VISIBLE_DEVICES=1,2 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
- 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
##### H200 test #####
- label: LM Eval Large Models (H200) # optional
timeout_in_minutes: 60
gpu: h200