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

Enabling "2 node" distributed tests in the AMD CI pipeline. (#32719)

Browse Source 
Signed-off-by: DCCS-4560 <alivanov@chi-mi325x-pod1-112.ord.vultr.cpe.ice.amd.com>
Co-authored-by: DCCS-4560 <alivanov@chi-mi325x-pod1-112.ord.vultr.cpe.ice.amd.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
This commit is contained in:
Alexei-V-Ivanov-AMD
2026-01-27 13:13:21 -06:00
committed by GitHub
parent 1cbccb6dba
commit 3c3c547ce0
2 changed files with 46 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
.buildkite/test-amd.yaml
View File

@@ -1278,7 +1278,7 @@ steps:
- label: 2 Node Tests (4 GPUs in total) # 16min
timeout_in_minutes: 30
mirror_hardwares: [amdexperimental]
mirror_hardwares: [amdexperimental, amdmultinode]
agent_pool: mi325_4
# grade: Blocking
working_dir: "/vllm-workspace/tests"
@@ -1292,15 +1292,15 @@ steps:
- tests/distributed/
- tests/examples/offline_inference/data_parallel.py
commands:
- # 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 | grep 'Same node test passed'
- NUM_NODES=2 torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=192.168.10.10 distributed/test_node_count.py | grep 'Node count test passed'
- # the following commands are for the first node, with ip 192.168.10.10 (ray environment already set up) | grep 'Same node test passed' | grep 'Node count test passed'
- 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
- NUM_NODES=2 torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=192.168.10.10 distributed/test_node_count.py
- python3 ../examples/offline_inference/data_parallel.py -dp=2 -tp=1 --dp-num-nodes=2 --dp-node-rank=0 --dp-master-addr=192.168.10.10 --dp-master-port=12345 --enforce-eager --trust-remote-code
- VLLM_MULTI_NODE=1 pytest -v -s distributed/test_multi_node_assignment.py
- VLLM_MULTI_NODE=1 pytest -v -s distributed/test_pipeline_parallel.py
- # the following commands are for the second node, with ip 192.168.10.11 (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 | grep 'Same node test passed'
- NUM_NODES=2 torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=192.168.10.10 distributed/test_node_count.py | grep 'Node count test passed'
- 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
- NUM_NODES=2 torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=192.168.10.10 distributed/test_node_count.py
- python3 ../examples/offline_inference/data_parallel.py -dp=2 -tp=1 --dp-num-nodes=2 --dp-node-rank=1 --dp-master-addr=192.168.10.10 --dp-master-port=12345 --enforce-eager --trust-remote-code
- label: Distributed Tests (2 GPUs) # 68min