biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[ROCm][CI] Remove deepep DBO tests on gfx90a (#37614)

Browse Source 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
This commit is contained in:
Andreas Karatzas
2026-03-20 04:07:07 -05:00
committed by GitHub
parent 9cfd4ebb5e
commit 37cd9fc107
1 changed files with 1 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
.buildkite/test-amd.yaml
View File

@@ -1402,7 +1402,7 @@ steps:
- label: Distributed Tests (2 GPUs)(H100-MI250) # TBD
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx90anightly, amdmi250]
agent_pool: mi250_2
agent_pool: mi325_2
num_gpus: 2
working_dir: "/vllm-workspace/"
source_file_dependencies:
@@ -1412,7 +1412,6 @@ steps:
- vllm/v1/attention/backends/
- vllm/v1/attention/selector.py
- tests/distributed/test_context_parallel.py
- tests/v1/distributed/test_dbo.py
- examples/offline_inference/data_parallel.py
- vllm/_aiter_ops.py
- vllm/platforms/rocm.py
@@ -1420,7 +1419,6 @@ steps:
- export TORCH_NCCL_BLOCKING_WAIT=1
- pytest -v -s tests/distributed/test_context_parallel.py
- 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=allgather_reducescatter --disable-nccl-for-dp-synchronization
- pytest -v -s tests/v1/distributed/test_dbo.py
#####################################################################################################################################
@@ -2594,21 +2592,16 @@ steps:
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi325]
agent_pool: mi325_2
num_gpus: 2
optional: true
working_dir: "/vllm-workspace/"
source_file_dependencies:
- vllm/distributed/
- vllm/v1/distributed/
- vllm/model_executor/layers/fused_moe/
- tests/distributed/test_context_parallel.py
- tests/v1/distributed/test_dbo.py
- examples/offline_inference/data_parallel.py
- vllm/_aiter_ops.py
- vllm/platforms/rocm.py
commands:
- export TORCH_NCCL_BLOCKING_WAIT=1
- pytest -v -s tests/distributed/test_context_parallel.py
- 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