From afc362260257ab16c2ffc6105678e1403c0475cb Mon Sep 17 00:00:00 2001 From: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com> Date: Sun, 18 Jan 2026 13:25:23 -0500 Subject: [PATCH] [CI] Move Distributed Tests from H200 -> H100 (#32555) --- .buildkite/test-pipeline.yaml | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/.buildkite/test-pipeline.yaml b/.buildkite/test-pipeline.yaml index 56bb3c23d5..fc9d92e3f2 100644 --- a/.buildkite/test-pipeline.yaml +++ b/.buildkite/test-pipeline.yaml @@ -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